A method and device for detecting the service life of a fuel cell

Abstract

In a fuel cell service life detection method and device provided in this application, a fuel cell baseline operating condition is first defined based on the fuel cell's application scenario. The characteristic matrix of the fuel cell operating under the baseline operating condition is input into a pre-trained prediction model to obtain the fuel cell's attenuation rate. The operating condition intensity is then combined with the attenuation rate of the fuel cell operating under the preset operating condition. Based on the operating condition intensity, a relationship between the operating condition intensity and the service life of the fuel cell under the baseline operating condition is established. The service life of the fuel cell is then determined based on the relationship analysis. In this solution, after obtaining the characteristic matrix based on the fuel cell operating under the baseline operating condition, the attenuation rate of the fuel cell is directly obtained by processing based on the prediction model. The service life of the fuel cell is directly obtained by analyzing and calculating the relationship between the operating condition intensity and the service life corresponding to the baseline operating condition, without having to wait for the fuel cell to operate to the end of its service life, thereby reducing the testing time.

Description

Technical Field

[0001] The present application relates to the field of fuel cells, and more specifically, to a method and device for detecting the service life of a fuel cell. Background Art

[0002] Hydrogen-oxygen fuel cell vehicles utilize a proton exchange membrane fuel cell (PEMFC) system at their core, using high-purity hydrogen to electrochemically react with oxygen in the air to generate electricity to propel the vehicle. Hydrogen-oxygen fuel cells are zero-emission or near-zero-emission onboard power solutions, offering advantages such as smooth operation, low noise, high economy, fast refueling, and strong environmental adaptability. With the growing severity of environmental pollution and global warming, hydrogen-oxygen fuel cells are gaining increasing attention as a vehicle powertrain solution.

[0003] To meet the growing durability requirements of fuel cell vehicles, the design durability of fuel cell systems (engines) has also risen sharply, reaching levels exceeding 10,000 hours. This makes verifying this design lifespan a major challenge in the fuel cell testing field.

[0004] Conventional fuel cell durability testing uses a "scenario simulation" approach, employing durability test cycles close to actual application scenarios. The relationship between test duration and test life is 1:1. However, testing times exceeding 10,000 hours significantly delays product development cycles and incurs significant testing costs. Summary of the Invention

[0005] In view of this, the present application provides a method for detecting the service life of a fuel cell, as follows:

[0006] A method for detecting the service life of a fuel cell, comprising:

[0007] Define the baseline operating conditions for fuel cell operation based on application scenarios;

[0008] Obtaining a characteristic matrix of the fuel cell operating under a defined reference operating condition;

[0009] Inputting the characteristic matrix of the reference operating condition into a pre-trained prediction model to obtain the attenuation rate of the fuel cell;

[0010] establishing a relationship between operating condition intensity and life under the reference operating condition based on the decay rate of the fuel cell, wherein the operating condition intensity is based on a ratio of at least two preset decay rates to the decay rate of the fuel cell, wherein the preset decay rates are decay rates of the fuel cell operating under the preset operating condition;

[0011] Based on the relationship between the operating intensity and life under the reference operating condition, the service life of the fuel cell is analyzed and determined.

[0012] Optionally, the above method, controlling the fuel cell to operate under a reference operating condition and obtaining a characteristic matrix of the reference operating condition, includes:

[0013] In the process of controlling the fuel cell to operate according to the reference operating condition for one cycle, collecting parameter values ​​of at least two operating condition parameters of the fuel cell;

[0014] acquiring current data and voltage data of the fuel cell during the process;

[0015] A characteristic matrix of the reference operating condition is obtained according to the parameter values ​​of the at least two operating condition parameters and the current data and voltage data.

[0016] Optionally, in the above method, obtaining the characteristic matrix of the reference operating condition according to the parameter values ​​of the at least two operating condition parameters and the current data and voltage data includes:

[0017] Selecting a complete operating cycle, dividing the current data of the fuel cell into at least two current intervals based on the current data of the fuel cell collected during the cycle, dividing the current data of the fuel cell into at least two voltage intervals based on the voltage data of the fuel cell collected during the cycle, calculating a first proportion of the duration of the current data in each interval that meets a preset current condition to the duration of the cycle, and obtaining current characteristics of the at least two current intervals;

[0018] Counting the at least two operating condition data of the fuel cell, calculating the proportion of the duration of the operating condition in each interval that meets the preset current condition to the duration of the cycle, and obtaining the operating condition characteristics of the at least two current intervals

[0019] Collecting voltage data of the fuel cell, calculating a second ratio of the duration of the voltage data in each interval meeting a preset voltage condition to the duration of the cycle, and obtaining voltage characteristics of the at least two voltage intervals;

[0020] The current characteristics, the voltage characteristics, and the operating condition characteristics are combined into a characteristic matrix of the reference operating condition in the form of column vectors.

[0021] Optionally, the above method further includes:

[0022] Obtaining a characteristic matrix of the fuel cell operating under at least two preset operating conditions;

[0023] The characteristic matrix operating under at least two preset working conditions is input into a pre-trained prediction model to obtain a preset attenuation rate of the fuel cell.

[0024] Optionally, in the above method, establishing a relationship between operating condition intensity and life under the reference operating condition based on the attenuation rate of the fuel cell includes:

[0025] Obtaining at least two preset attenuation rates and at least two preset lifespans corresponding to the fuel cell under at least two preset operating conditions;

[0026] Calculating the operating condition intensity of the fuel cell under the reference operating condition based on the at least two preset attenuation rates and the attenuation rate of the fuel cell under the reference operating condition;

[0027] creating a durability characteristic curve according to at least two operating condition intensities of the fuel cell under the reference operating condition and at least two preset lifespans of the fuel cell;

[0028] The functional relationship between the working condition strength and the life span is obtained by fitting the durability characteristic curve.

[0029] Optionally, in the above method, analyzing and determining the service life of the fuel cell based on the relationship between the operating intensity and the service life under the reference operating condition includes:

[0030] Based on the functional relationship between the operating condition intensity and the lifespan, the service life of the fuel cell under the target operating condition intensity is calculated.

[0031] Optionally, the above method, before defining the baseline operating condition of the fuel cell according to the application scenario, further includes:

[0032] The prediction model is trained based on at least two training operating conditions of the fuel cell.

[0033] Optionally, in the above method, the training prediction model based on at least two training operating conditions of the fuel cell includes:

[0034] Selecting one training condition from the at least two training conditions in sequence;

[0035] Acquire a characteristic matrix in each training operating condition and a performance decay rate of the fuel cell to obtain a characteristic matrix set and a performance decay rate set;

[0036] A prediction model is trained based on the feature matrix set as input and the performance decay rate set as output.

[0037] Optionally, the above method of obtaining the attenuation rate of the fuel cell under any training condition includes:

[0038] controlling the fuel cell to operate according to the training operating condition for at least two cycles, and detecting the attenuation value of the fuel cell according to a preset detection cycle;

[0039] Counting the training life of the fuel cell, where the training life is the service life of the fuel cell under the training working condition;

[0040] The attenuation rate of the fuel cell is calculated according to the attenuation value and the training life.

[0041] A device for detecting the service life of a fuel cell, comprising:

[0042] Definition module, used to define the baseline operating conditions of the fuel cell according to the application scenario;

[0043] A matrix module, configured to obtain a characteristic matrix of the fuel cell operating under the reference operating conditions;

[0044] a relationship establishing module, which establishes a relationship between operating condition intensity and life under the reference operating condition based on the attenuation rate of the fuel cell, wherein the operating condition intensity is a ratio of a preset attenuation rate to the attenuation rate of the fuel cell, and the preset attenuation rate is the attenuation rate of the fuel cell when operating under the preset operating condition;

[0045] The analysis module is used to analyze and determine the service life of the fuel cell based on the relationship between the operating condition intensity and the service life under the reference operating condition.

[0046] Through the above technical solutions, it can be seen that the present application provides a method for detecting the service life of a fuel cell. First, the baseline operating condition of the fuel cell is defined according to the application scenario of the fuel cell. The characteristic matrix of the fuel cell operating under the baseline operating condition is input into a pre-trained prediction model to obtain the attenuation rate of the fuel cell. The operating condition intensity is obtained by combining the attenuation rate of the fuel cell operating under the preset operating condition. The relationship between the operating condition intensity and the life of the fuel cell under the baseline operating condition is established based on the operating condition intensity, and then the service life of the fuel cell is determined based on the analysis of the relationship. In this solution, after obtaining the characteristic matrix based on the fuel cell operating under the baseline operating condition, the attenuation rate of the fuel cell can be obtained by directly processing it based on the prediction model, and the service life of the fuel cell can be directly obtained by analyzing and calculating based on the established relationship between the operating condition intensity and the life under the baseline operating condition, without waiting for the fuel cell to run to the end of its service life, thereby reducing the test time. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without any creative work.

[0048] Figure 1This is a flow chart of Example 1 of a method for detecting the service life of a fuel cell provided in this application;

[0049] Figure 2 This is a flow chart of Example 2 of a method for detecting the service life of a fuel cell provided in this application;

[0050] Figure 3 A schematic diagram of fuel cell life detection in Example 2 of a fuel cell service life detection method provided in this application;

[0051] Figure 4 This is a schematic diagram of the interval division in Example 2 of a method for detecting the service life of a fuel cell provided in this application;

[0052] Figure 5 This is a flow chart of Example 3 of a method for detecting the service life of a fuel cell provided in this application;

[0053] Figure 6 This is a durability characteristic curve diagram in Example 3 of a method for detecting the service life of a fuel cell provided in this application;

[0054] Figure 7 This is a flow chart of Example 4 of a method for detecting the service life of a fuel cell provided in this application;

[0055] Figure 8 This is a flow chart of Example 5 of a method for detecting the service life of a fuel cell provided in this application;

[0056] Figure 9 A schematic structural diagram of an embodiment of a fuel cell service life detection device provided in this application;

[0057] Figure 10 This is a schematic structural diagram of an electronic device embodiment provided by this application. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0059] like Figure 1 The figure is a flow chart of Example 1 of a method for detecting the service life of a fuel cell provided by the present application, and the method comprises the following steps:

[0060] Step S101: defining a baseline operating condition for a fuel cell according to an application scenario;

[0061] The fuel cell may include: a single fuel cell, a short fuel cell stack, a fuel cell module, a fuel cell system, etc. The present application does not limit the specific form of the fuel cell.

[0062] The reference operating condition is the operating condition of the fuel cell whose service life is to be tested.

[0063] Specifically, the specific conditions of the reference operating condition can be set according to different application scenarios. For example, the reference operating condition can be the actual vehicle operating condition of a fuel cell used in a bus, or it can be a standard operating condition specified by national standards or enterprise standards.

[0064] Specifically, the baseline operating characteristics of the fuel cell are reflected in the operating condition settings of the fuel cell. The operating conditions of the fuel cell are the types of physical parameters of the external input and output of the fuel cell during the operation of the fuel cell product, generally including operating temperature, fuel supply pressure, fuel supply flow, fuel supply humidity, ambient temperature, ambient pressure, intake humidity, pressure difference, etc.

[0065] Step S102: obtaining a characteristic matrix of the fuel cell operating under a defined reference operating condition;

[0066] The fuel cell is controlled to operate under the reference operating condition to obtain a characteristic matrix of the reference operating condition.

[0067] Specifically, the characteristic matrix includes data related to operating condition parameters, current, voltage, etc.

[0068] Step S103: inputting the characteristic matrix of the reference operating condition into a pre-trained prediction model to obtain the attenuation rate of the fuel cell;

[0069] A prediction model is pre-trained, and the prediction model is obtained by training with a feature matrix of multiple training working conditions as input and a decay rate corresponding to the fuel cell under the training working conditions as output.

[0070] Specifically, the characteristic matrix of the reference operating condition is input into the prediction model as input information, and the prediction model processes and outputs the attenuation rate of the fuel cell.

[0071] The prediction model is trained based on the feature matrices corresponding to multiple training conditions as input and the corresponding preset life as output.

[0072] Step S104: establishing a relationship between operating intensity and life under the reference operating condition based on the attenuation rate of the fuel cell;

[0073] The operating condition intensity is based on a ratio of at least two preset decay rates to the decay rate of the fuel cell, and the preset decay rate is the decay rate of the fuel cell when operating under a preset operating condition.

[0074] The operating condition intensity is the ratio of the fuel cell performance attenuation rate under a preset operating condition to the fuel cell performance attenuation rate under a reference operating condition.

[0075] In a specific implementation, the processor executing this solution may pre-store detection data, such as the attenuation rate under the multiple preset working conditions, which may be the detection value obtained when training the prediction model, or the parameter value that can be used to calculate the attenuation rate.

[0076] If the attenuation rate is calculated based on the parameter value, the process of calculating the attenuation rate is as follows:

[0077] Obtaining a characteristic matrix of the fuel cell operating under at least two preset operating conditions;

[0078] The characteristic matrix operating under at least two preset working conditions is input into a pre-trained prediction model to obtain a preset attenuation rate of the fuel cell.

[0079] Specifically, the characteristic matrix of the fuel cell operating under preset working conditions may be pre-stored in the electronic device. After the characteristic matrix is ​​obtained, it is input into the trained prediction model to obtain the preset attenuation rate of the fuel cell.

[0080] In the specific implementation, the same prediction model is used to analyze the attenuation rate under the preset working conditions and the attenuation rate under the benchmark working conditions. The corresponding attenuation rate is obtained by analyzing and processing the characteristic matrix under the preset working conditions and the characteristic matrix under the benchmark working conditions, which reduces the influence of other conditions in the process of analyzing the attenuation rate and improves the accuracy of predicting the service life of the fuel cell.

[0081] Step S105: Analyze and determine the service life of the fuel cell based on the relationship between the operating intensity and the service life under the reference operating condition.

[0082] Specifically, it is known that under the baseline operating condition, based on the relationship between the operating condition intensity and the life, and the operating condition intensity is the ratio of the fuel cell attenuation rate under the baseline operating condition, then by selecting the corresponding operating condition intensity, the service life of the fuel cell under the baseline operating condition can be determined.

[0083] In specific implementation, the service life of the fuel cell obtained through detection can be fed back to the vehicle controller, so that the vehicle controller can evaluate the maintenance cycle of the fuel cell system based on the feedback of the current fuel cell life, and notify the user through the display instrument to perform regular maintenance on the fuel cell in time, thereby improving the durability of the fuel cell.

[0084] In summary, this embodiment provides a method for detecting the service life of a fuel cell. First, a baseline operating condition for the fuel cell is defined based on the fuel cell's application scenario. The characteristic matrix of the fuel cell operating under the baseline operating condition is input into a pre-trained prediction model to obtain the fuel cell's attenuation rate. The operating condition intensity is then obtained by combining the attenuation rate of the fuel cell operating under the preset operating condition. Based on the operating condition intensity, a relationship between the operating condition intensity and the service life of the fuel cell under the baseline operating condition is established. The service life of the fuel cell is then determined based on the analysis of this relationship. In this solution, after obtaining the characteristic matrix based on the fuel cell operating under the baseline operating condition, the attenuation rate of the fuel cell can be obtained by directly processing it based on the prediction model. The service life of the fuel cell can then be directly obtained by analyzing and calculating the relationship between the operating condition intensity and the service life corresponding to the baseline operating condition, without having to wait for the fuel cell to operate to the end of its service life, thereby reducing the test time.

[0085] like Figure 2 The figure is a flow chart of Example 2 of a method for detecting the service life of a fuel cell provided by the present application, and the method comprises the following steps:

[0086] Step S201: defining a base operating condition of a fuel cell according to an application scenario;

[0087] Among them, step S201 is consistent with step S101 in embodiment 1 and is not described in detail in this embodiment.

[0088] Step S202: collecting parameter values ​​of at least two operating condition parameters of the fuel cell during the process of controlling the fuel cell to operate according to the reference operating condition for one cycle;

[0089] According to the reference operating condition, the fuel cell is controlled to operate for a cycle, and during the operation, parameter values ​​of a plurality of operating condition parameters of the fuel cell are collected.

[0090] Specifically, the operating condition parameters may include operating temperature, fuel supply pressure, fuel supply flow rate, fuel supply humidity, ambient temperature, ambient pressure, etc., but are not limited thereto.

[0091] Step S203: Acquire current data and voltage data of the fuel cell during the process;

[0092] Accordingly, during the operation of the fuel cell, current data and voltage data of the fuel cell are obtained.

[0093] The current data and the voltage data are electrical energy generated during the operation of the fuel cell, and the current data and the voltage data represent the electrical energy generation situation of the fuel cell.

[0094] Step S204: obtaining a characteristic matrix of the reference operating condition according to the parameter values ​​of the at least two operating condition parameters and the current data and voltage data;

[0095] The characteristic matrix of the reference operating condition is obtained by processing the parameter values ​​of the multiple operating condition parameters and the current data and voltage data.

[0096] Specifically, the plurality of operating condition parameters characterize the operating conditions of the fuel cell, which are conditions for testing the durability of the fuel cell.

[0097] like Figure 3 What is shown is a schematic diagram of fuel cell life detection, where the operating condition parameters include anode fuel supply metering ratio, anode fuel supply pressure, cathode fuel supply metering ratio, cathode fuel supply pressure, operating temperature, etc. Under the operating condition parameters, the fuel cell has voltage output and current output, and the voltage and current are used to power electrical equipment.

[0098] It should be noted that the characteristic matrix characterizes the operating condition parameters under the baseline operating conditions and the situation of the fuel cell generating electrical energy. By inputting the prediction model based on the characteristic matrix, the prediction model can obtain the attenuation rate of the fuel cell based on the analysis of the operating conditions of the fuel cell in one cycle.

[0099] Herein, step S204 includes the following steps:

[0100] Step S2041: selecting a complete operating cycle, dividing the cycle into at least two current intervals based on the current data of the fuel cell collected during the cycle, and dividing the cycle into at least two voltage intervals based on the voltage data of the fuel cell collected during the cycle;

[0101] Step S2042: Counting the current data of the fuel cell, calculating a first ratio of the duration of each interval meeting the preset current condition to the duration of the cycle, and obtaining current characteristics of the at least two current intervals;

[0102] Specifically, during the operating cycle, the duration of the current data that meets the preset current conditions is calculated. Based on this duration and the duration of the fuel cell operating cycle, a first ratio is calculated, and the ratios in each current interval are obtained in turn, that is, the current characteristics of the multiple time intervals are obtained.

[0103] Specifically, the maximum current value Imax and the minimum current value Imin of the fuel cell in a complete operating cycle are counted, and the current range of the difference between the maximum current value and the minimum current value is divided into multiple current intervals at equal intervals, such as n intervals, each of which is (Imax-Imin) / n, where n is an integer greater than 1; the number of current data points appearing in each current interval is counted, and this number is multiplied by the sampling time of each data point to obtain the operating time of the interval; the operating time of each interval is divided by the total operating time in turn to obtain the duration proportion α of each interval i-j , where α represents the ratio, i and j represent the interval numbers, for example: C1 is "interval 1".

[0104] like Figure 4 The diagram below shows a time interval diagram. The horizontal axis represents time (hours) and the vertical axis represents current (amperes). In this diagram, the curve represents the output current of the fuel cell. The vertical axis divides the range of 550-900 into five current zones, C1-C5. In this figure, the interval of 550-620 is C1, the interval of 620-690 is C2, the interval of 690-760 is C3, the interval of 760-830 is C4, and the interval of 830-900 is C5. Among them, the interval between 550-690 is C12, the interval between 550-760 is C13, the interval between 550-830 is C14, and the interval between 550-900 is C15; similarly, the interval between 620-760 is C23, the interval between 620-830 is C24, and the interval between 620-900 is C25; the interval between 620-760 is C23, the interval between 690-830 is C34, and the interval between 690-900 is C35; and the interval between 760-900 is C45.

[0105] It should be noted that the analysis parameters are not limited to current, but can be extended to current density (m A / cm 2 ) and other current-related characterization parameters.

[0106] Step S2043: collecting voltage data of the fuel cell, calculating a second ratio of the duration of each interval meeting the preset voltage condition to the duration of the cycle, and obtaining voltage characteristics of the at least two voltage intervals;

[0107] Specifically, in each cycle, the duration of the voltage data that meets the preset voltage conditions is calculated, and based on the duration and the duration of the fuel cell operation cycle, a second ratio is calculated, and the ratios in each voltage interval are obtained in turn, that is, the voltage characteristics of the multiple time intervals are obtained.

[0108] Specifically, the maximum voltage value Umax and the minimum voltage value Umin of the fuel cell in one cycle are counted, and the voltage range of the difference between the maximum voltage value and the minimum voltage value is divided into multiple voltage intervals at equal intervals, such as n intervals, each of which is (Umax-Umin) / n, where n is an integer greater than 1; the number of voltage data points appearing in each voltage interval is counted, and this number is multiplied by the sampling time of each data point to obtain the running time of the interval; the running time of each interval is divided by the total running time in turn to obtain the duration proportion β of each interval. i-j , where β represents the ratio, i and j represent the interval numbers, for example: C1 is "interval 1".

[0109] Specifically, based on the current intervals divided in step S2042, the specific values ​​of the operating condition parameters of the fuel cell in each current interval are counted, the average value and standard deviation of each interval are calculated, and then multiplied by the proportion of the fuel cell operating time in the corresponding current interval (i.e., the first proportion) to obtain the operating condition characteristics corresponding to the operating condition parameters.

[0110] For example, the average value of the fuel stoichiometric ratio is μ stoic,i-j , the standard deviation is σ stoic,i-j , which is equal to the first ratio α i-j Multiply by to get the characteristic α of the fuel stoichiometric ratio i-j μ stoic,i-j and α i-j ·σ stoic,i-j , where stoic represents the fuel stoichiometric ratio.

[0111] Step S2045: The current characteristics, the voltage characteristics, and the operating condition characteristics are combined into a characteristic matrix of the reference operating condition in the form of column vectors.

[0112] The current characteristics, voltage characteristics and operating condition characteristics obtained in the above steps are combined into a characteristic matrix of the reference operating condition according to column vectors.

[0113] Specifically, the current feature is one column, the voltage feature is one column, and the number of columns of the operating condition feature is related to the number of parameters involved. One parameter corresponds to two columns (one column is obtained based on the average value, and one column is obtained based on the standard deviation).

[0114] Step S205: inputting the characteristic matrix of the reference operating condition into a pre-trained prediction model to obtain the attenuation rate of the fuel cell;

[0115] Step S206: establishing a relationship between operating intensity and life under the reference operating condition based on the attenuation rate of the fuel cell;

[0116] Step S207: Analyze and determine the service life of the fuel cell based on the relationship between the operating condition intensity and the service life under the reference operating condition.

[0117] Among them, steps S205-207 are consistent with steps S103-105 in Example 1 and are not described in detail in this embodiment.

[0118] In summary, in a method for detecting the service life of a fuel cell provided in this embodiment, the method controls the fuel cell to operate under a baseline operating condition and obtains a characteristic matrix for the baseline operating condition, including: collecting parameter values ​​of at least two operating condition parameters of the fuel cell during a cycle of controlling the fuel cell to operate according to the baseline operating condition; obtaining current data and voltage data of the fuel cell during the process; and obtaining the characteristic matrix for the baseline operating condition based on the parameter values ​​of the at least two operating condition parameters and the current and voltage data. In this solution, the fuel cell is controlled to operate under the baseline operating condition for a cycle, and during operation, the parameter values ​​of the operating condition parameters and corresponding voltage and current data are collected, and the characteristic matrix for the baseline operating condition is obtained by processing the collected parameter values, voltage and current data. The characteristic matrix represents the operating condition parameters under the baseline operating condition and the electrical energy generated by the fuel cell. The characteristic matrix is ​​input into a prediction model based on the characteristic matrix, so that the prediction model can analyze the operating condition of the fuel cell over a cycle and obtain the attenuation rate of the fuel cell.

[0119] like Figure 5 The figure shown is a flow chart of Example 3 of a method for detecting the service life of a fuel cell provided by the present application, the method comprising the following steps:

[0120] Step S501: defining a base operating condition of a fuel cell according to an application scenario;

[0121] Step S502: obtaining a characteristic matrix of the fuel cell operating under a defined reference operating condition;

[0122] Step S503: inputting the characteristic matrix of the reference operating condition into a pre-trained prediction model to obtain the attenuation rate of the fuel cell;

[0123] Among them, steps S501-503 are consistent with steps S101-103 in Example 1 and are not described in detail in this embodiment.

[0124] Step S504: obtaining at least two preset attenuation rates and at least two preset lifespans corresponding to the fuel cell under at least two preset operating conditions;

[0125] The preset decay rate and the preset lifespan are obtained, and the preset decay rate and the preset lifespan are in a corresponding relationship.

[0126] It should be noted that there is a negative correlation between the intensity of the operating condition and the actual life of the fuel cell operating under the operating condition. The greater the intensity of the operating condition, the shorter the life of the fuel cell.

[0127] Correspondingly, the preset lifespan is the lifespan corresponding to the preset operating condition, and the corresponding lifespan can be stored when the preset operating condition is stored.

[0128] In a specific implementation, when the prediction model is pre-trained, the fuel cell can be controlled to operate based on the preset operating condition, and the operation reaches the training life of the fuel cell, and the training life is recorded as the preset life corresponding to the preset operating condition.

[0129] In a specific implementation, the preset attenuation rate can be a decay rate value stored based on a preset operating condition, or a characteristic matrix stored based on a preset operating condition. When the service life of the fuel cell is detected, the decay rate corresponding to the preset operating condition is calculated based on a prediction model.

[0130] Step S505: Calculating the operating condition intensity of the fuel cell under the reference operating condition based on the at least two preset attenuation rates and the attenuation rate of the fuel cell under the reference operating condition;

[0131] The operating condition intensity is based on a ratio of at least two preset decay rates to the decay rate of the fuel cell under a baseline operating condition.

[0132] Specifically, the preset attenuation rate is divided by the attenuation rate under the reference operating condition to obtain the operating condition intensity, that is, the operating condition intensity = the preset attenuation rate / the attenuation rate of the fuel cell.

[0133] For example, the attenuation rate set is {ξ1,ξ2,ξ3,...}, and the attenuation rate of the fuel cell under the reference operating condition is ξ0. Dividing the two, the obtained operating condition intensity set is {ξ1 / ξ0,ξ2 / ξ0,ξ3 / ξ0,...}.

[0134] Step S506: creating a durability characteristic curve according to at least two operating condition intensities of the fuel cell under the reference operating condition and at least two preset lifespans of the fuel cell;

[0135] It should be noted that the preset lifespan is set corresponding to the preset decay rate, that is, one preset decay rate corresponds to one preset lifespan.

[0136] Specifically, a two-dimensional coordinate system is created, with the working condition intensity ξ as the vertical coordinate and the preset life t of the fuel cell as the horizontal coordinate. i ,ξ i / ξ0) is input into the two-dimensional coordinate system to obtain a scatter plot, and then a linear regression fitting is performed on the characteristic scatter data to obtain a durability characteristic curve.

[0137] In a specific implementation, the set of operating condition intensities can also be fed back to the vehicle controller, so that the vehicle controller can reduce the degree of power request to the fuel cell system by dynamically adjusting the energy matching strategy based on the feedback of the current operating condition intensity, thereby making the fuel cell operating condition more moderate and thus improving the durability of the fuel cell.

[0138] In specific implementations, the operating condition intensity set can also be fed back to the fuel cell system. The fuel cell system dynamically adjusts the control parameters of the operating conditions based on the fed-back current operating condition intensity to make the fuel cell operating conditions more suitable, thereby improving the durability of the fuel cell.

[0139] Step S507: obtaining a functional relationship between working condition strength and lifespan according to the durability characteristic curve fitting;

[0140] Wherein, a corresponding function is obtained based on the durability characteristic curve, and the function is a functional relationship between the working condition intensity and the preset life.

[0141] For example, Y=f(X), where Y is the working intensity and X is the preset life.

[0142] like Figure 6 The figure shows a durability characteristic curve. The x-axis of the two-dimensional coordinate system represents the fuel cell lifespan (in hours, logarithm to base 10), and the y-axis represents the operating intensity. This coordinate system contains four points: (2.6, 2.4), (3.2, 1.7), (3.7, 1.4), and (4.3, 1). The durability characteristic curve is fitted based on these four points, as shown by the dashed line in the figure. The function corresponding to this durability characteristic curve is y = -0.7637x + 4.2057. The fatigue limit of this fuel cell is a 10% performance degradation, and the lifespan corresponding to an operating intensity of 1 is the design lifespan.

[0143] Step S508: Based on the functional relationship between the operating condition intensity and the lifespan, the service life of the fuel cell under the target operating condition intensity is calculated.

[0144] Specifically, based on the functional relationship, when the working condition intensity corresponding to the determined life is the same as the current reference working condition intensity, the working condition intensity is set to 1, the target attenuation rate corresponding to the working condition intensity is determined, and the corresponding x value is determined based on the function.

[0145] For example, if the function is y=-0.7637x+4.2057, then when y=1, the value of x is 4.1796. By looking up the logarithmic table, the service life of the fuel cell can be obtained.

[0146] Based on this functional relationship, when the working condition intensity corresponding to the determined life is half of the current benchmark working condition intensity, the working condition intensity is set to 0.5, the target attenuation rate corresponding to the working condition intensity is determined, and the corresponding x value is determined based on the function.

[0147] For example, if the function is y=-0.7637x+4.2057, then when y=0.5, the value of x is 4.8523. By looking up the logarithmic table, the service life of the fuel cell can be obtained.

[0148] It should be noted that, in a specific implementation, the service life of the fuel cell obtained by detection may be compared with the design life. If the service life is greater than the design life, it is considered that the design durability requirement is met.

[0149] In summary, in a method for detecting the service life of a fuel cell provided in this embodiment, at least two preset attenuation rates and at least two preset lifespans corresponding to the fuel cell under at least two preset operating conditions are obtained; the operating condition intensity of the fuel cell under the reference operating condition is calculated based on the at least two preset attenuation rates and the attenuation rate of the fuel cell under the reference operating condition; a durability characteristic curve is created based on the at least two operating condition intensities of the fuel cell under the reference operating condition and the at least two preset lifespans of the fuel cell; a functional relationship between the operating condition intensity and the lifespan is obtained by fitting the durability characteristic curve; and the service life of the fuel cell under the target operating condition intensity is calculated based on the functional relationship between the operating condition intensity and the lifespan. In this solution, a fuel cell durability characteristic curve is established to determine the functional relationship between the operating condition intensity and the lifespan, and then a rapid evaluation of the durability of the fuel cell product is achieved based on this functional relationship.

[0150] like Figure 7 The figure is a flow chart of Example 4 of a method for detecting the service life of a fuel cell provided by the present application, and the method comprises the following steps:

[0151] Step S701: training a prediction model based on at least two training operating conditions of a fuel cell;

[0152] Among them, the working condition intensity of this training condition is greater than the working condition intensity of the baseline condition. Since the intensity of the training condition is greater, it can shorten the overall test time.

[0153] The operating condition parameters used in different training working conditions may be different or the same, and the values ​​of the various operating condition parameters (ie, working condition intensities) are different.

[0154] It should be noted that the fuel cell can be multiple fuel cells using the same setting parameters, and a training condition of different intensity is specified for each fuel cell to reduce the overall time required to operate the fuel cell based on the training condition and improve the efficiency of training.

[0155] It should be noted that after the prediction model is trained, it can detect the service life of fuel cells under various benchmark operating conditions. Compared with the 1:1 test time and detection life under each benchmark operating condition, the overall detection time is shorter and the detection efficiency is higher.

[0156] Moreover, due to the long test cycle and high test cost, traditional durability tests generally use a single sample. In this solution, durability test samples with different working conditions and strengths are used. Compared with the traditional single-sample long-cycle durability test, multiple samples ensure the accuracy of the durability test and improve the credibility of the test.

[0157] Step S702: defining a base operating condition of the fuel cell according to an application scenario;

[0158] Step S703: inputting the characteristic matrix of the reference operating condition into a pre-trained prediction model to obtain the attenuation rate of the fuel cell;

[0159] Step S704: obtaining a characteristic matrix of the fuel cell operating under a defined reference operating condition;

[0160] Step S705: establishing a relationship between operating intensity and life under the reference operating condition based on the attenuation rate of the fuel cell;

[0161] Step S706: Analyze and determine the service life of the fuel cell based on the relationship between the operating condition intensity and the service life under the reference operating condition.

[0162] Among them, steps S702-706 are consistent with steps S101-105 in Example 1 and are not described in detail in this embodiment.

[0163] In summary, in the method for detecting the service life of a fuel cell provided in this embodiment, a prediction model is trained in advance using training conditions of multiple working condition intensities so that it can process the feature matrix subsequently input thereto and output the attenuation rate of the fuel cell, thereby ensuring the accuracy of subsequent detection and improving credibility.

[0164] like Figure 8 The figure shows a flow chart of Example 5 of a method for detecting the service life of a fuel cell provided by the present application, which method includes the following steps:

[0165] Step S801: selecting a training condition from at least two training conditions in sequence;

[0166] Among them, in this application, the prediction model is trained based on multiple training conditions. In this solution, multiple different training conditions are determined, and one training condition is selected in turn to control the fuel cell to run a complete cycle under the training condition.

[0167] Step S802: Acquire the characteristic matrix of each training operating condition and the performance decay rate of the fuel cell to obtain a characteristic matrix set and a performance decay rate set;

[0168] During each training operating condition, parameter values ​​of at least two operating condition parameters of the fuel cell are collected, and current data and voltage data of the fuel cell are collected during the process to obtain a feature matrix under the training operating condition.

[0169] It should be noted that the process of obtaining the feature matrix for each training working condition can refer to the process of determining the feature matrix in the reference working condition in the aforementioned embodiment, which will not be described in detail in this embodiment.

[0170] Specifically, the feature matrices under each training condition are combined to obtain a feature matrix set.

[0171] For example, the feature matrices under the training condition are M1, M2, M3, ..., and the obtained feature matrix set is {M1, M2, M3, ...}.

[0172] Wherein, obtaining the attenuation rate of the fuel cell in any training condition includes:

[0173] Step S8021: controlling the fuel cell to operate according to the training working condition for at least two cycles, and detecting the attenuation value of the fuel cell according to a preset detection cycle;

[0174] The fuel cell is controlled to operate cyclically under the training condition, and the attenuation value of the fuel cell is detected according to a preset detection cycle.

[0175] The process of detecting the attenuation rate of the fuel cell includes: generating a polarization curve (IV curve) according to voltage data and current data of the fuel cell, and calculating the attenuation value according to the polarization curve.

[0176] Specifically, a fixed current value (such as 300A) is selected, and the fuel cell voltage value is obtained according to the polarization curve. As the fuel cell operates under the training condition, the stack voltage under the current condition shows a downward trend, that is, attenuates.

[0177] The calculation process of the attenuation value is as follows: select the current I0, obtain the voltage V under the current from the polarization curve data i , i is an integer greater than 0, wherein V0 is the fuel cell voltage obtained from the first polarization curve obtained under the training condition; as the operation under the training condition is carried out, V1, V2, ... are obtained, and the attenuation value ΔV = (V0-V i ) / V0. When △V is greater than the design index, the fatigue limit is reached.

[0178] Step S8022: Counting the training life of the fuel cell;

[0179] The training life is the service life of the fuel cell under the training working condition.

[0180] The fuel cell is cyclically operated under the training condition, and the performance attenuation value of the fuel cell is detected until the performance attenuation of the fuel cell exceeds the design value and reaches the fatigue limit, at which time the life of the fuel cell is counted.

[0181] It should be noted that the training life of the fuel cell under various training conditions obtained by statistics during the training of the prediction model is the preset life of the fuel cell to be subsequently tested under the reference condition.

[0182] Step S8023: Calculate the attenuation rate of the fuel cell according to the attenuation value and the training life.

[0183] The decay rate is the ratio of the decay value to the training life, and the formula is as follows:

[0184] ξ i =ΔV / t i

[0185] Among them, ξ i is the attenuation rate; △V is the attenuation value; t i is the life of the fuel cell under the training condition, that is, the training life.

[0186] For example, the decay rates obtained under various training conditions are ξ1, ξ2, ξ3, ..., and the decay rate set obtained is {ξ1, ξ2, ξ3, ...}.

[0187] Step S803: training a prediction model based on the feature matrix set as input and the performance decay rate set as output;

[0188] Among them, a nonlinear correlation model (ie, a prediction model) between the feature matrix and the performance decay rate set is established through mathematical tools.

[0189] The mathematical tool may be a nonlinear least squares method, a neural network, etc., but is not limited thereto.

[0190] Specifically, the prediction model is trained and adjusted based on the feature matrix set and the performance decay rate set, so that the model input is the feature matrix and the output result is the performance decay rate.

[0191] Step S804: defining a base operating condition of the fuel cell according to the application scenario;

[0192] Step S805: inputting the characteristic matrix of the reference operating condition into a pre-trained prediction model to obtain the attenuation rate of the fuel cell;

[0193] Step S806: obtaining a characteristic matrix of the fuel cell operating under a defined reference operating condition;

[0194] Step S807: establishing a relationship between operating condition intensity and life under the reference operating condition based on the attenuation rate of the fuel cell;

[0195] Step S808: Analyze and determine the service life of the fuel cell based on the relationship between the operating intensity and the service life under the reference operating condition.

[0196] Among them, steps S804-808 are consistent with steps S702-706 in Example 6 and are not described in detail in this embodiment.

[0197] In summary, in a method for detecting the service life of a fuel cell provided in this embodiment, the operation of the fuel cell is controlled in turn based on each of a plurality of training working conditions, and the characteristic matrix under each training working condition and the performance decay rate of the fuel cell are obtained based on the operation process. A characteristic matrix set and a performance decay rate set are established based on the characteristic matrix and the performance decay rate under each training working condition, and a prediction model is trained based on the above two sets so that the prediction model inputs the characteristic matrix and outputs the performance decay rate.

[0198] Corresponding to the above-mentioned embodiment of a method for detecting the service life of a fuel cell provided in the present application, the present application also provides an embodiment of a device applying the method for detecting the service life of a fuel cell.

[0199] like Figure 9 The figure shows a schematic diagram of a fuel cell service life detection device according to embodiment 1 of the present application. The device includes the following structures: a definition module 901, a matrix module 902, a relationship establishment module 903, and an analysis module 904.

[0200] The definition module 901 is used to define the baseline operating conditions of the fuel cell according to the application scenario;

[0201] The matrix module 902 is used to obtain a characteristic matrix of the fuel cell operating under the reference operating conditions;

[0202] The relationship establishing module 903 establishes a relationship between the operating condition intensity and the life under the reference operating condition based on the attenuation rate of the fuel cell, wherein the operating condition intensity is a ratio of a preset attenuation rate to the attenuation rate of the fuel cell, and the preset attenuation rate is the attenuation rate of the fuel cell when operating under the preset operating condition;

[0203] The analysis module 904 is configured to analyze and determine the service life of the fuel cell based on the relationship between the operating intensity and the service life under the reference operating condition.

[0204] Optionally, the matrix module is used to:

[0205] In the process of controlling the fuel cell to operate according to the reference operating condition for one cycle, collecting parameter values ​​of at least two operating condition parameters of the fuel cell;

[0206] acquiring current data and voltage data of the fuel cell during the process;

[0207] A characteristic matrix of the reference operating condition is obtained according to the parameter values ​​of the at least two operating condition parameters and the current data and voltage data.

[0208] Optionally, the matrix module is specifically used to:

[0209] Select a complete operating cycle, divide the current data of the fuel cell into at least two current intervals according to the statistics of the current data of the fuel cell in the cycle, and divide the voltage data of the fuel cell into at least two voltage intervals according to the statistics of the voltage data of the fuel cell in the cycle

[0210] Collecting the current data of the fuel cell, calculating a first ratio of the duration of each interval meeting the preset current condition to the duration of the cycle of the current data, and obtaining current characteristics of the at least two current intervals;

[0211] Counting the at least two operating condition data of the fuel cell, calculating the proportion of the duration of the operating condition in each interval that meets the preset current condition to the duration of the cycle, and obtaining the operating condition characteristics of the at least two current intervals

[0212] Collecting voltage data of the fuel cell, calculating a second ratio of the duration of the voltage data in each interval meeting a preset voltage condition to the duration of the cycle, and obtaining voltage characteristics of the at least two voltage intervals;

[0213] The current characteristics, the voltage characteristics, and the operating condition characteristics are combined into a characteristic matrix of the reference operating condition in the form of column vectors.

[0214] Optionally, also include:

[0215] An acquisition module is used to obtain a characteristic matrix of a fuel cell operating under at least two preset operating conditions; and input the characteristic matrix operating under at least two preset operating conditions into a pre-trained prediction model to obtain a preset attenuation rate of the fuel cell.

[0216] Optionally, the relationship establishing module is used to:

[0217] Obtaining at least two preset attenuation rates and at least two preset lifespans corresponding to the fuel cell under at least two preset operating conditions;

[0218] Calculating the operating condition intensity of the fuel cell under the reference operating condition based on the at least two preset attenuation rates and the attenuation rate of the fuel cell under the reference operating condition;

[0219] creating a durability characteristic curve according to at least two operating condition intensities of the fuel cell under the reference operating condition and at least two preset lifespans of the fuel cell;

[0220] The functional relationship between the working condition strength and the life span is obtained by fitting the durability characteristic curve.

[0221] Optionally, the relationship establishing module is specifically configured to:

[0222] Based on the functional relationship between the operating condition intensity and the lifespan, the service life of the fuel cell under the target operating condition intensity is calculated.

[0223] Optionally, also include:

[0224] A training module is used to train a prediction model based on at least two training operating conditions of the fuel cell.

[0225] Optional training module for:

[0226] Selecting one training condition from the at least two training conditions in sequence;

[0227] Acquire a characteristic matrix in each training operating condition and a performance decay rate of the fuel cell to obtain a characteristic matrix set and a performance decay rate set;

[0228] A prediction model is trained based on the feature matrix set as input and the performance decay rate set as output.

[0229] Optional training module, specifically for:

[0230] controlling the fuel cell to operate according to the training operating condition for at least two cycles, and detecting the attenuation value of the fuel cell according to a preset detection cycle;

[0231] Counting the training life of the fuel cell, where the training life is the service life of the fuel cell under the training working condition;

[0232] The attenuation rate of the fuel cell is calculated according to the attenuation value and the training life.

[0233] It should be noted that the functional explanation of each structure in this embodiment refers to the explanation in the aforementioned method embodiment and is not described in detail in this embodiment.

[0234] In summary, the present embodiment provides a fuel cell service life detection device. First, a fuel cell baseline operating condition is defined based on the fuel cell's application scenario. The characteristic matrix of the fuel cell operating under the baseline operating condition is input into a pre-trained prediction model to obtain the fuel cell's attenuation rate. The operating condition intensity is obtained by combining the attenuation rate of the fuel cell operating under the preset operating condition. The relationship between the operating condition intensity and the service life of the fuel cell under the baseline operating condition is established based on the operating condition intensity. The service life of the fuel cell is then determined based on the analysis of this relationship. In this solution, after obtaining the characteristic matrix based on the fuel cell operating under the baseline operating condition, the attenuation rate of the fuel cell can be obtained by directly processing it based on the prediction model. The service life of the fuel cell can be directly obtained by analyzing and calculating based on the established relationship between the operating condition intensity and the service life under the baseline operating condition, without having to wait for the fuel cell to operate until the end of its service life, thereby reducing the test time.

[0235] Corresponding to the above-mentioned embodiment of a method for detecting the service life of a fuel cell provided in the present application, the present application also provides an embodiment of an electronic device to which the method for detecting the service life of a fuel cell is applied.

[0236] like Figure 10 The figure shows a schematic diagram of the structure of an electronic device embodiment provided by the present application, which includes the following structures: a data interaction module 1001, a data storage module 1002 and a data processing module 1003; Figure 10 The direction of the arrow in the middle indicates the direction of data transmission.

[0237] The data interaction module 1001 is used to collect data during the operation of the fuel cell and send the information processed by the data processing module;

[0238] Specifically, the data includes parameter values ​​of at least two operating condition parameters, current data, and voltage data. The operating condition parameters are explained with reference to the aforementioned method embodiment and are not described in detail in this embodiment.

[0239] In specific implementations, the data interaction module can select communication protocols such as CAN (Controller Area Network), RS232, RS485 or Ethernet for communication interaction, and can collect analog signals such as current, voltage, and resistance, as well as digital signals such as PWM (Pulse Width Modulation), frequency, and 0 / 1 (binary).

[0240] The data storage module 1002 is used to store the collected data and the data generated during the operation;

[0241] Specifically, the storage space of the data storage module includes a cache area and a long-term storage area.

[0242] The data obtained under the baseline working conditions can be stored in the cache area, while the trained prediction model is stored in the long-term storage area.

[0243] The data processing module 1003 is used to perform calculations on the data collected by the data interaction module 1001 and output the lifespan and operating intensity of the fuel cell.

[0244] Specifically, the data processing module may adopt a structure with strong computing capability, such as a CPU (central processing unit).

[0245] In a specific implementation, the electronic device is installed together with the fuel cell on an application platform (such as a fuel cell test bench, a fuel cell system or a fuel cell vehicle, etc.). The fuel cell operates according to the set working conditions. The data interaction module collects the battery current, voltage and operating condition parameter information of the fuel cell in real time and stores it in the data storage module. The data calculation module calls the fuel cell operating data within a certain time period to obtain the working condition feature array, inputs it into the trained prediction model to obtain the working condition intensity, and calculates the life of the fuel cell based on the working condition intensity, and feeds back to the application platform through the data interaction module.

[0246] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices provided in the embodiments, since they correspond to the methods provided in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0247] The above description of the provided embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features provided herein.

Claims

1. A method for detecting the service life of a fuel cell, characterized in that: include: Define the baseline operating conditions for fuel cell operation based on application scenarios; Obtaining a characteristic matrix of the fuel cell operating under a defined reference operating condition; Inputting the characteristic matrix of the reference operating condition into a pre-trained prediction model to obtain the attenuation rate of the fuel cell; establishing a relationship between operating condition intensity and life under the reference operating condition based on the decay rate of the fuel cell, wherein the operating condition intensity is based on a ratio of at least two preset decay rates to the decay rate of the fuel cell, wherein the preset decay rates are decay rates of the fuel cell operating under the preset operating condition; Analyze and determine the service life of the fuel cell based on the relationship between the operating intensity and life under the baseline operating condition; The step of controlling the fuel cell to operate under a reference operating condition and obtaining a characteristic matrix of the reference operating condition includes: In the process of controlling the fuel cell to operate according to the reference operating condition for one cycle, collecting parameter values ​​of at least two operating condition parameters of the fuel cell; acquiring current data and voltage data of the fuel cell during the process; A characteristic matrix of the reference operating condition is obtained according to the parameter values ​​of the at least two operating condition parameters and the current data and voltage data.

2. The method according to claim 1, characterized in that The step of obtaining the characteristic matrix of the reference operating condition according to the parameter values ​​of the at least two operating condition parameters and the current data and the voltage data includes: Selecting a complete operating cycle, dividing the cycle into at least two current intervals based on current data of the fuel cell collected during the cycle, and dividing the cycle into at least two voltage intervals based on voltage data of the fuel cell collected during the cycle; Collecting the current data of the fuel cell, calculating a first ratio of the duration of each interval meeting the preset current condition to the duration of the cycle of the current data, and obtaining current characteristics of the at least two current intervals; Collecting data on at least two operating conditions of the fuel cell, calculating the proportion of the duration of each interval in which the operating condition meets the preset current condition to the duration of the cycle, and obtaining operating condition characteristics of the at least two current intervals; Collecting voltage data of the fuel cell, calculating a second ratio of the duration of the voltage data in each interval meeting a preset voltage condition to the duration of the cycle, and obtaining voltage characteristics of the at least two voltage intervals; The current characteristics, the voltage characteristics, and the operating condition characteristics are combined into a characteristic matrix of the reference operating condition in the form of column vectors.

3. The method according to claim 1, characterized in that Also includes: Obtaining a characteristic matrix of the fuel cell operating under at least two preset operating conditions; The characteristic matrix operating under at least two preset working conditions is input into a pre-trained prediction model to obtain a preset attenuation rate of the fuel cell.

4. The method according to claim 1, wherein The relationship between the operating condition intensity and the life span under the reference operating condition is established based on the attenuation rate of the fuel cell, including: Obtaining at least two preset attenuation rates and at least two preset lifespans corresponding to the fuel cell under at least two preset operating conditions; Calculating the operating condition intensity of the fuel cell under the reference operating condition based on the at least two preset attenuation rates and the attenuation rate of the fuel cell under the reference operating condition; creating a durability characteristic curve according to at least two operating condition intensities of the fuel cell under the reference operating condition and at least two preset lifespans of the fuel cell; The functional relationship between the working condition strength and the life span is obtained by fitting the durability characteristic curve.

5. The method according to claim 4, characterized in that The analyzing and determining the service life of the fuel cell based on the relationship between the operating intensity and the service life under the reference operating condition includes: Based on the functional relationship between the operating condition intensity and the lifespan, the service life of the fuel cell under the target operating condition intensity is calculated.

6. The method according to claim 1, characterized in that Before defining the baseline operating conditions of the fuel cell according to the application scenario, the following steps are also included: The prediction model is trained based on at least two training operating conditions of the fuel cell.

7. The method according to claim 6, characterized in that The at least two training operating condition training prediction models based on the fuel cell include: Selecting one training condition from the at least two training conditions in sequence; Acquire a characteristic matrix in each training operating condition and a performance decay rate of the fuel cell to obtain a characteristic matrix set and a performance decay rate set; A prediction model is trained based on the feature matrix set as input and the performance decay rate set as output.

8. The method according to claim 7, characterized in that Obtaining the attenuation rate of the fuel cell under any training condition, including: controlling the fuel cell to operate according to the training operating condition for at least two cycles, and detecting the attenuation value of the fuel cell according to a preset detection cycle; Counting the training life of the fuel cell, where the training life is the service life of the fuel cell under the training working condition; The attenuation rate of the fuel cell is calculated according to the attenuation value and the training life.

9. A fuel cell service life detection device, characterized in that: include: Definition module, used to define the baseline operating conditions of the fuel cell according to the application scenario; A matrix module, configured to obtain a characteristic matrix of the fuel cell operating under the reference operating conditions; a relationship establishing module, which establishes a relationship between operating condition intensity and life under the reference operating condition based on the attenuation rate of the fuel cell, wherein the operating condition intensity is a ratio of a preset attenuation rate to the attenuation rate of the fuel cell, and the preset attenuation rate is the attenuation rate of the fuel cell when operating under the preset operating condition; an analysis module, configured to analyze and determine the service life of the fuel cell based on a relationship between the operating condition intensity and the service life under the reference operating condition; The step of controlling the fuel cell to operate under a reference operating condition and obtaining a characteristic matrix of the reference operating condition includes: In the process of controlling the fuel cell to operate according to the reference operating condition for one cycle, collecting parameter values ​​of at least two operating condition parameters of the fuel cell; acquiring current data and voltage data of the fuel cell during the process; A characteristic matrix of the reference operating condition is obtained according to the parameter values ​​of the at least two operating condition parameters and the current data and voltage data.

Images