Attenuation identification method for fuel cell automobile stack operation stability

Abstract

The invention relates to the technical field of fuel cells, in particular to an attenuation identification method for fuel cell automobile stack operation stability, and the method comprises the steps: obtaining a first data set of a fuel cell stack of a fuel cell automobile, and processing the first data set to obtain an effective operation data set; determining the first and second operation characteristic time intervals and the corresponding first and second effective operation data sets, carrying out fitting calculation to obtain respective voltage fitting values, and further analyzing to obtain a fuel cell stack fitting determination coefficient; and calculating a relative deviation value of the fuel cell stack fitting determination coefficients of the first and second operation characteristic time intervals, and determining whether the operation stability of the fuel cell stack is attenuated or not based on the relative deviation value. According to the invention, a bench test is carried out without dismounting the fuel cell stack from a vehicle through a traditional means, the test resource demand is greatly saved, the operation stability change condition of the fuel cell stack in all time periods can be obtained, and a technical support is provided for the overhaul and maintenance of an electric pile product.

Description

Technical Field

[0001] The present invention relates to the technical field of fuel cells, and particularly to a method for identifying the attenuation of the operating stability of a fuel cell stack for a fuel cell vehicle. Background Art

[0002] During the actual road driving process of a fuel cell vehicle, due to continuous influences of factors such as vehicle acceleration and deceleration, road surface vibration excitation, environmental temperature and humidity changes, and air pollutants, the output performance of the fuel cell engine will show a certain degree of attenuation as the vehicle driving mileage and the engine working time increase, manifested as a decrease in the output power of the fuel cell stack under rated conditions and a decrease in the operating stability of the fuel cell stack.

[0003] However, the currently publicly available documents of the prior art do not involve the monitoring, judgment, and identification of the operating stability of the fuel cell stack during the actual road driving process of a fuel cell vehicle. Moreover, the test resources and costs required for disassembling and testing the fuel cell stack of the vehicle are too high to meet the situation of more than 10,000 vehicles in the "3 + 2" urban agglomeration. Therefore, there is an urgent need for an efficient, fast, and easy-to-operate method for identifying and analyzing the operating stability state of the fuel cell stack, so as to provide technical support for the enterprise to perform the overhaul and maintenance of the fuel cell stack products. Summary of the Invention

[0004] To achieve the above object, the present invention provides the following technical solutions: According to the first aspect of the present invention, the present invention claims a method for identifying the attenuation of the operating stability of a fuel cell stack for a fuel cell vehicle, including: Obtaining a first data set of the fuel cell stack of the fuel cell vehicle, and cleaning and screening the first data set to obtain an effective operating data set of the fuel cell stack; Setting an operating state identification time interval of the fuel cell stack, and determining a first operating characteristic time interval and a second operating characteristic time interval of the fuel cell stack in combination with a first operating characteristic moment and a second operating characteristic moment of the fuel cell stack; Based on the effective operating data set, obtaining a first effective operating data set and a second effective operating data set corresponding to the first operating characteristic time interval and the second operating characteristic time interval; According to the first effective operating data set and the second effective operating data set, using the least squares method to perform curve fitting between the voltage and current of the fuel cell stack, and obtaining voltage fitting values corresponding to the first operating characteristic time interval and the second operating characteristic time interval respectively; The fitting determination coefficient of the fuel cell stack for the first operating characteristic time interval and the second operating characteristic time interval is calculated based on the first effective operating data set, the second effective operating data set, and the voltage fitting values of the first operating characteristic time interval and the second operating characteristic time interval. Calculate the relative deviation value of the fitting determination coefficient of the fuel cell stack for the first operating characteristic time interval and the second operating characteristic time interval, and determine whether the operating stability of the fuel cell stack has decayed based on the relative deviation value.

[0005] Further, the obtaining of the first data set of the fuel cell stack of the fuel cell vehicle further includes: Obtain the vehicle upload data of the fuel cell vehicle from the moment when data uploading starts to the current moment, including the information sending time, the fuel cell current, and the fuel cell voltage, and record it as the first data set.

[0006] Further, the cleaning and screening of the first data set to obtain the effective operating data set of the fuel cell stack includes: Set the minimum power threshold of the fuel cell stack, the minimum and maximum thresholds of the fuel cell current effectiveness, and the minimum and maximum thresholds of the fuel cell voltage effectiveness. Perform data cleaning and screening on the first data set according to multiple thresholds to obtain the effective operating data set of the fuel cell stack.

[0007] Further, the setting of the operating state recognition time interval of the fuel cell stack, and the determination of the first operating characteristic time interval and the second operating characteristic time interval of the fuel cell stack in combination with the first operating characteristic moment and the second operating characteristic moment of the fuel cell stack further includes: Set the operating state recognition time interval of the fuel cell stack. Extract the first operating characteristic moment and the second operating characteristic moment of the fuel cell stack, and calculate to obtain the operating characteristic time interval of the first fuel cell stack and the operating characteristic time interval of the second fuel cell stack.

[0008] Further, the curve fitting between the voltage and current of the fuel cell stack is performed by using the least squares method according to the first effective operating data set and the second effective operating data set to obtain the voltage fitting values corresponding to the first operating characteristic time interval and the second operating characteristic time interval respectively, and further includes: According to the first effective operating data set, perform curve fitting between the voltage and current of the fuel cell stack by using the least squares method to obtain the voltage fitting value corresponding to the first operating characteristic time interval. Based on the second effective operation dataset, curve fitting is performed between the voltage and current of the fuel cell stack using the least squares method to obtain the voltage fitting value corresponding to the second operation characteristic time interval.

[0009] Further, calculating the fitting determination coefficients of the fuel cell stack for the first operation characteristic time interval and the second operation characteristic time interval based on the first effective operation dataset, the second effective operation dataset, and the voltage fitting values of the first operation characteristic time interval and the second operation characteristic time interval further includes: Calculating the fitting determination coefficient of the fuel cell stack for the first operation characteristic time interval based on the first effective operation dataset and the voltage fitting value of the first operation characteristic time interval; Calculating the fitting determination coefficient of the fuel cell stack for the second operation characteristic time interval based on the second effective operation dataset and the voltage fitting value of the second operation characteristic time interval.

[0010] Further, calculating the fitting determination coefficient of the fuel cell stack for the first operation characteristic time interval based on the first effective operation dataset and the voltage fitting value of the first operation characteristic time interval further includes: Calculating the average value, sum of squared residuals, and total sum of squares of the fitting voltage of the fuel cell stack for the first operation characteristic time interval based on the first effective operation dataset and the voltage fitting value of the fuel cell stack for the first operation characteristic time interval; Calculating the fitting determination coefficient of the fuel cell stack for the first operation characteristic time interval based on the sum of squared residuals and total sum of squares of the fuel cell stack fitting for the first operation characteristic time interval.

[0011] Further, calculating the fitting determination coefficient of the fuel cell stack for the second operation characteristic time interval based on the second effective operation dataset and the voltage fitting value of the second operation characteristic time interval further includes: Calculating the average value of the fitting voltage, sum of squared residuals, and total sum of squares of the fuel cell stack for the second operation characteristic time interval based on the second effective operation dataset and the voltage fitting value of the fuel cell stack for the second operation characteristic time interval; Calculating the fitting determination coefficient of the fuel cell stack for the second operation characteristic time interval based on the sum of squared residuals and total sum of squares of the fuel cell stack fitting for the second operation characteristic time interval.

[0012] Further, calculating the relative deviation value of the fitting determination coefficients of the fuel cell stack for the first operation characteristic time interval and the second operation characteristic time interval, and determining whether the operation stability of the fuel cell stack has decayed based on the relative deviation value further includes: Compare the relative deviation value with the set reference threshold to determine whether the operating stability of the fuel cell stack has decayed; If the relative deviation value is greater than the set reference threshold, it indicates that the operating stability of the fuel cell stack has decayed; Otherwise, it indicates that the operating stability of the fuel cell stack has not decayed.

[0013] The present invention relates to the technical field of fuel cells, and particularly to a method for detecting the decay of the operating stability of a fuel cell stack in a fuel cell vehicle based on a big data platform. A first data set of the fuel cell stack of the fuel cell vehicle is obtained and processed to obtain an effective operating data set; the first and second operating characteristic time intervals and the corresponding first and second effective operating data sets are determined, and the respective voltage fitting values are obtained by fitting calculation, and further analysis is performed to obtain the fitting determination coefficient of the fuel cell stack; the relative deviation value of the fitting determination coefficient of the fuel cell stack in the first and second operating characteristic time intervals is calculated, and based on the relative deviation value, it is determined whether the operating stability of the fuel cell stack has decayed. The present invention does not need to disassemble and assemble the fuel cell stack from the vehicle by traditional means for bench testing, greatly saving the test resource requirements, and at the same time, it can also obtain the change of the operating stability of the fuel cell stack in all time periods, providing technical support for the inspection and maintenance of the fuel cell stack products. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a flowchart of a method for detecting the decay of the operating stability of a fuel cell stack in a fuel cell vehicle claimed in an embodiment of the present invention; Figure 2 It is a schematic diagram of the test results of a method for detecting the decay of the operating stability of a fuel cell stack in a fuel cell vehicle claimed in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0015] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0016] The terms "first", "second", and "third" in the present invention are only for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", and "third" may explicitly or implicitly include at least one of such features. In the description of the present invention, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the drawings). If the specific posture changes, the directional indications will also change accordingly. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0017] Reference to "an embodiment" herein means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0018] According to the first embodiment of the present invention, referring to Figure 1 , the present invention claims a method for identifying the attenuation of the operating stability of a fuel cell stack for a fuel cell vehicle, including: S1. Obtain a first data set of the fuel cell stack of the fuel cell vehicle, and clean and screen the first data set to obtain an effective operating data set of the fuel cell stack; S2. Set the operating state identification time interval of the fuel cell stack, and determine a first operating characteristic time interval and a second operating characteristic time interval of the fuel cell stack in combination with a first operating characteristic moment and a second operating characteristic moment of the fuel cell stack; S3. Based on the effective operating data set, obtain a first effective operating data set and a second effective operating data set corresponding to the first operating characteristic time interval and the second operating characteristic time interval; S4. According to the first effective operating data set and the second effective operating data set, perform curve fitting between the voltage and current of the fuel cell stack by using the least square method to obtain voltage fitting values corresponding to the first operating characteristic time interval and the second operating characteristic time interval; S5. Calculate the fitting determination coefficient of the fuel cell stack for the first operating characteristic time interval and the second operating characteristic time interval based on the voltage fitting values of the first effective operating data set, the second effective operating data set, the first operating characteristic time interval, and the second operating characteristic time interval. S6. Calculate the relative deviation value of the fitting determination coefficient of the fuel cell stack for the first operating characteristic time interval and the second operating characteristic time interval, and determine whether the operating stability of the fuel cell stack has decayed based on the relative deviation value.

[0019] Further, in S1, it further includes: Obtain the vehicle upload data of the fuel cell vehicle from the start time of data upload to the current time, including the information sending time, the fuel cell current, and the fuel cell voltage, denoted as the first data set.

[0020] Among them, in this embodiment, based on the fuel cell vehicle big data platform, extract the vehicle upload data of the fuel cell vehicle from the start time of data upload to the current time, covering the information sending time t, the fuel cell current and the fuel cell voltage , denoted as the first data set S.

[0021] Further, in S1, it further includes: Set the minimum power threshold of the fuel cell stack, the minimum and maximum thresholds of the fuel cell current validity, and the minimum and maximum thresholds of the fuel cell voltage validity. Perform data cleaning and screening on the first data set according to multiple thresholds to obtain the effective operating data set of the fuel cell stack.

[0022] Among them, in this embodiment, set the minimum power threshold of the fuel cell stack , the minimum threshold of the fuel cell current validity and the maximum threshold , the minimum threshold of the fuel cell voltage validity and the maximum threshold , perform data cleaning and screening on the first data set S to obtain the effective operating data set of the fuel cell stack ( );

[0023] Wherein represents the fuel cell current, represents the fuel cell voltage, represents the minimum power threshold of the fuel cell stack, and represent the minimum and maximum thresholds of the fuel cell current validity, and represent the minimum threshold and the maximum threshold of the fuel cell voltage effectiveness, indicating the belonging symbol; Combined with the vehicle upload data time interval (s), the cumulative operating time of the fuel cell stack is calculated (h);

[0024] wherein represents the total number of rows of the effective operating data set of the fuel cell stack .

[0025] Furthermore, the S2 further includes: Set the operating state recognition time interval of the fuel cell stack; Extract the first operating characteristic moment and the second operating characteristic moment of the fuel cell stack, and calculate the operating characteristic time interval of the first fuel cell stack and the operating characteristic time interval of the second fuel cell stack.

[0026] Among them, in this embodiment, the operating state recognition time interval of the fuel cell stack is set to , extract the first operating characteristic moment of the first fuel cell stack and the second operating characteristic moment of the second fuel cell stack , calculate that the first operating characteristic time interval is , , and the second operating characteristic time interval is , ; Specifically, it needs to satisfy: ; Furthermore, in this embodiment, the S3 further includes: Based on the effective operating data set of the fuel cell stack Extract the first effective operating data set corresponding to the first operating characteristic time interval and the second effective operating data set corresponding to the second operating characteristic time interval ; ; .

[0027] Furthermore, the S4 further includes: According to the first effective operating data set, use the least squares method to perform curve fitting between the voltage and current of the fuel cell stack to obtain the voltage fitting value corresponding to the first operating characteristic time interval; According to the second effective operation data set, the least squares method is used to perform curve fitting between the voltage and current of the fuel cell stack, and the voltage fitting value corresponding to the second operation characteristic time interval is obtained.

[0028] Among them, in this embodiment, for the effective operation data set of the first fuel cell stack , the least squares method is used to perform curve fitting between the fuel cell stack voltage and the fuel cell current, and the fuel cell stack performance fitting formula for the first operation characteristic time interval is obtained ; Wherein represents the fuel cell stack voltage fitting value for the first operation characteristic time interval, represents the number of single cells of the fuel cell stack, represents the fuel cell stack performance fitting constant for the first operation characteristic time interval, represents the natural logarithm operation, represents the fuel cell current, represents the membership symbol; For the effective operation data set of the second fuel cell stack , the least squares method is used to perform curve fitting between the fuel cell stack voltage and the fuel cell current, and the fuel cell stack performance fitting formula for the second operation characteristic time interval is obtained; ; Wherein represents the fuel cell stack voltage fitting value for the second operation characteristic time interval, represents the number of single cells of the fuel cell stack, represents the fuel cell stack performance fitting constant for the second operation characteristic time interval, represents the natural logarithm operation, represents the fuel cell current, represents the membership symbol.

[0029] Furthermore, step S5 further includes: Calculating the fuel cell stack fitting determination coefficient for the first operation characteristic time interval based on the first effective operation data set and the voltage fitting value for the first operation characteristic time interval; Calculating the fuel cell stack fitting determination coefficient for the second operation characteristic time interval based on the second effective operation data set and the voltage fitting value for the second operation characteristic time interval.

[0030] Furthermore, calculating the fuel cell stack fitting determination coefficient for the first operation characteristic time interval based on the first effective operation data set and the voltage fitting value for the first operation characteristic time interval further includes: Based on the voltage fitting values of the fuel cell stack for the first effective operation dataset and the first operation characteristic time interval, calculate the average value, sum of squared residuals, and total sum of squares of the fuel cell stack fitting voltage for the first operation characteristic time interval; Based on the sum of squared residuals and total sum of squares of the fuel cell stack fitting for the first operation characteristic time interval, calculate the coefficient of determination of the fuel cell stack fitting for the first operation characteristic time interval.

[0031] Further, calculating the coefficient of determination of the fuel cell stack fitting for the second operation characteristic time interval based on the voltage fitting values for the second effective operation dataset and the second operation characteristic time interval further includes: Based on the voltage fitting values of the fuel cell stack for the second effective operation dataset and the second operation characteristic time interval, calculate the average value, sum of squared residuals, and total sum of squares of the fuel cell stack fitting voltage for the second operation characteristic time interval; Based on the sum of squared residuals and total sum of squares of the fuel cell stack fitting for the second operation characteristic time interval, calculate the coefficient of determination of the fuel cell stack fitting for the second operation characteristic time interval.

[0032] Wherein, in this embodiment, based on the first effective operation dataset and the fuel cell stack performance fitting formula for the first operation characteristic time interval , calculate the average value of the fuel cell stack fitting voltage for the first operation characteristic time interval , sum of squared residuals and total sum of squares ;

[0033]

[0034]

[0035] Where represents the number of rows of the first effective operation dataset ; Based on the second effective operation dataset and the fuel cell stack performance fitting formula for the second operation characteristic time interval , calculate the average value of the fuel cell stack fitting voltage for the second operation characteristic time interval , sum of squared residuals and total sum of squares ;

[0036]

[0037]

[0038] wherein represents the number of rows of the second effective operating data set ; the sum of squared fitting residuals of the fuel cell stack based on the first operating characteristic time interval and the total sum of squares and the sum of squared fitting residuals of the fuel cell stack in the second operating characteristic time interval and the total sum of squares , and the coefficient of determination of the fuel cell stack fitting in the first operating characteristic time interval is calculated and the coefficient of determination of the fuel cell stack fitting in the second operating characteristic time interval ; ; .

[0039] Furthermore, calculating the relative deviation value of the coefficient of determination of the fuel cell stack fitting in the first operating characteristic time interval and the second operating characteristic time interval, and determining whether the operating stability of the fuel cell stack decays based on the relative deviation value further includes: comparing the relative deviation value with a set reference threshold to determine whether the operating stability of the fuel cell stack decays; if the relative deviation value is greater than the set reference threshold, it indicates that the operating stability of the fuel cell stack decays; otherwise, it indicates that the operating stability of the fuel cell stack does not decay.

[0040] Wherein, in this embodiment, the relative deviation value between the coefficient of determination of the fuel cell stack fitting in the first operating characteristic time interval and the coefficient of determination of the fuel cell stack fitting in the second operating characteristic time interval is calculated ;

[0041] wherein represents taking the absolute value; comparing the relative deviation value with the set reference threshold , and determining whether the operating stability of the fuel cell stack decays; if , it indicates that the operating stability of the fuel cell stack decays; if , it indicates that the operating stability of the fuel cell stack does not decay.

[0042] The following is an illustration for a specific implementation test case: The selected type of fuel cell vehicle is a heavy-duty truck. Since June 2022, it has been sending data to the big data platform. The cumulative driving mileage is 112,788.3 km. The demonstration urban agglomeration where the vehicle is located is the Beijing-Tianjin-Hebei urban agglomeration. The rated power of the fuel cell stack is 70 kW, the number of single cells in the fuel cell stack is 242, and the information sending frequency is 0.1 Hz; Based on the fuel cell vehicle big data platform, extract the vehicle upload data of the fuel cell vehicle from the moment when data uploading starts to the current moment, covering the information sending time t, the fuel cell current and the fuel cell voltage , denoted as the first data set S; The data set S is a matrix of 1,931,778 rows and 3 columns. The first column is the information sending time, the second column is the fuel cell current, and the third column is the fuel cell voltage; ; Set the minimum power threshold of the fuel cell stack , the minimum threshold of the fuel cell current effectiveness and the maximum threshold , the minimum threshold of the fuel cell voltage effectiveness and the maximum threshold , and perform data cleaning and screening on the first data set S to obtain the effective operation data set of the fuel cell stack ( ); ; Among them represents the fuel cell current, represents the fuel cell voltage, represents the minimum power threshold of the fuel cell stack, and represent the minimum and maximum thresholds of the fuel cell current effectiveness, and represent the minimum and maximum thresholds of the fuel cell voltage effectiveness; Set the minimum power threshold of the fuel cell stack to 100 W, the minimum threshold of the fuel cell current effectiveness to 2 A, the maximum threshold to 1000 A, the minimum threshold of the fuel cell voltage effectiveness to 5 V, and the maximum threshold to 1000 V. Perform data cleaning and screening on the first data set S to obtain the effective operation data set of the fuel cell stack ( ); ; Effective operation data set It is a matrix with 645,084 rows and 3 columns. The first column is the information sending time, the second column is the fuel cell current, and the third column is the fuel cell voltage; Combined with the vehicle upload data time interval (s), the cumulative operation time of the fuel cell stack is calculated (h); ; Among them represents the total number of rows of the effective operation data set of the fuel cell stack ; The vehicle information sending frequency is 0.1 Hz, and the vehicle upload data time interval is calculated to be 10 s; The effective operation data set is a matrix with 645,084 rows and 3 columns, and the cumulative operation time of the fuel cell stack is calculated to be 1791.9 h;

[0043] Set the fuel cell stack operation status recognition time interval as t_interval, extract the first fuel cell stack operation characteristic moment and the second fuel cell stack operation characteristic moment , calculate that the operation characteristic time interval of the first fuel cell stack is , , and the operation characteristic time interval of the second fuel cell stack is , ;

[0044] Set the time interval t_interval to 20 h, set the first fuel cell stack operation characteristic moment to be 50 h, and set the second fuel cell stack operation characteristic moment to be 1500 h; Calculate that the first operation characteristic time interval is [50, 70], and the second operation characteristic time interval is [1500, 1520]; Based on the effective operation data set of the fuel cell stack Extract the corresponding and of the operation characteristic time interval of the first fuel cell stack;

[0045]

[0046] is a matrix with 7200 rows and 3 columns;

[0047] is a matrix of 7200 rows and 3 columns;

[0048] For , perform curve fitting between the fuel cell stack voltage and the fuel cell current by the least squares method to obtain the fuel cell stack performance fitting formula for the first operating characteristic time interval;

[0049] where represents the fuel cell stack voltage fitting value for the first operating characteristic time interval, represents the number of single cells of the fuel cell stack, represents the fuel cell stack performance fitting constant for the first operating characteristic time interval, represents the natural logarithm operation, represents the fuel cell current; After calculation, the fuel cell stack performance fitting formula for the first operating characteristic time interval is obtained;

[0050] For , perform curve fitting between the fuel cell stack voltage and the fuel cell current by the least squares method to obtain the fuel cell stack performance fitting formula for the second operating characteristic time interval;

[0051] where represents the fuel cell stack voltage fitting value for the second operating characteristic time interval, represents the number of single cells of the fuel cell stack, represents the fuel cell stack performance fitting constant for the second operating characteristic time interval, represents the natural logarithm operation, represents the fuel cell current; After calculation, the fuel cell stack performance fitting formula for the second operating characteristic time interval is obtained;

[0052] Based on the effective operation data set of the first fuel cell stack and the fuel cell stack performance fitting formula for the first operating characteristic time interval , calculate the average fuel cell stack fitting voltage for the first operating characteristic time interval, the residual square and the total sum of squares ;

[0053]

[0054]

[0055] where represents the number of rows; After calculation, the average fitted voltage of the fuel cell stack in the first operating characteristic time interval , the sum of squared residuals and the total sum of squares ;

[0056]

[0057]

[0058] Based on the performance fitting formula of the fuel cell stack in the second operating characteristic time interval , calculate the average fitted voltage of the fuel cell stack in the second operating characteristic time interval , the sum of squared residuals and the total sum of squares ;

[0059]

[0060]

[0061] where represents the number of rows; After calculation, the average fitted voltage of the fuel cell stack in the second operating characteristic time interval , the sum of squared residuals and the total sum of squares ;

[0062]

[0063]

[0064] Based on the sum of squared residuals and the total sum of squares of the fuel cell stack in the first operating characteristic time interval, and the sum of squared residuals and the total sum of squares Calculate the coefficient of determination of the fuel cell stack fitting for the first operating characteristic time interval and the coefficient of determination of the fuel cell stack fitting for the second operating characteristic time interval ; ; ; After calculation, the coefficient of determination of the fuel cell stack fitting for the first operating characteristic time interval and the coefficient of determination of the fuel cell stack fitting for the second operating characteristic time interval ; ; ; Calculate the relative deviation value between the coefficient of determination of the fuel cell stack fitting for the first operating characteristic time interval and the coefficient of determination of the fuel cell stack fitting for the second operating characteristic time interval ; ; ; where denotes taking the absolute value; Refer to Figure 2 After calculation, the relative deviation value between the coefficient of determination of the fuel cell stack fitting for the first operating characteristic time interval and the coefficient of determination of the fuel cell stack fitting for the second operating characteristic time interval ; ; ; Compare the relative deviation value with the set reference threshold , and determine whether the operating stability of the fuel cell stack has decayed; if , it indicates that the operating stability of the fuel cell stack has decayed; if , it indicates that the operating stability of the fuel cell stack has not decayed; Set the reference threshold to 0.2. Since the relative deviation value is greater than the reference threshold , it is determined that the operating stability of the fuel cell stack has decayed.

[0065] In several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be in electrical, mechanical, or other forms.

[0066] In addition, each functional unit in various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units. The above is only the implementation manner of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

[0067] The specific implementation manners of the invention have been described in detail above, but they are only examples. The present invention is not limited to the specific implementation manners described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the present invention. Therefore, all equal transformations, modifications, improvements, etc. made without departing from the spirit and principle of the present invention should be covered by the scope of the present invention.

Claims

1. A method for identifying the degradation of the operating stability of a fuel cell vehicle stack, characterized in that, Including: Obtain a first data set of the fuel cell stack of the fuel cell vehicle, and clean and screen the first data set to obtain an effective operation data set of the fuel cell stack; Set the operation state recognition time interval of the fuel cell stack, and determine the first operation characteristic time interval and the second operation characteristic time interval of the fuel cell stack in combination with the first operation characteristic moment and the second operation characteristic moment of the fuel cell stack; Based on the effective operation data set, obtain a first effective operation data set and a second effective operation data set corresponding to the first operation characteristic time interval and the second operation characteristic time interval; According to the first effective operation data set and the second effective operation data set, use the least squares method to perform curve fitting between the voltage and current of the fuel cell stack to obtain voltage fitting values corresponding to the first operation characteristic time interval and the second operation characteristic time interval respectively; Calculate the fitting determination coefficients of the fuel cell stack for the first operation characteristic time interval and the second operation characteristic time interval based on the first effective operation data set, the second effective operation data set, and the voltage fitting values of the first operation characteristic time interval and the second operation characteristic time interval; Calculate the relative deviation value of the fitting determination coefficients of the fuel cell stack for the first operation characteristic time interval and the second operation characteristic time interval, and determine whether the operation stability of the fuel cell stack has decayed based on the relative deviation value.

2. The decay identification method for the operation stability of a fuel cell vehicle stack according to claim 1, wherein, The obtaining of the first data set of the fuel cell stack of the fuel cell vehicle further includes: Obtain the vehicle upload data of the fuel cell vehicle from the moment when data upload starts to the current moment, including the information sending time, the fuel cell current, and the fuel cell voltage, denoted as the first data set.

3. A decay identification method for the operating stability of a fuel cell vehicle stack according to claim 1, characterized in that The cleaning and screening of the first data set to obtain the effective operation data set of the fuel cell stack includes: Set the minimum power threshold of the fuel cell stack, the minimum and maximum thresholds of the fuel cell current validity, and the minimum and maximum thresholds of the fuel cell voltage validity; Perform data cleaning and screening on the first data set according to multiple thresholds to obtain an effective operation data set of the fuel cell stack.

4. A decay identification method for the operation stability of a fuel cell vehicle stack according to claim 1, characterized in that, The setting of the operation state recognition time interval of the fuel cell stack and the determination of the first operation characteristic time interval and the second operation characteristic time interval of the fuel cell stack in combination with the first operation characteristic moment and the second operation characteristic moment of the fuel cell stack further includes: Set the operation state recognition time interval of the fuel cell stack; Extract the first operation characteristic moment and the second operation characteristic moment of the fuel cell stack, and calculate the operation characteristic time interval of the first fuel cell stack and the operation characteristic time interval of the second fuel cell stack.

5. A decay identification method for the operating stability of a fuel cell vehicle stack according to claim 1, characterized in that The performing of curve fitting between the voltage and current of the fuel cell stack using the least squares method according to the first effective operation data set and the second effective operation data set to obtain voltage fitting values corresponding to the first operation characteristic time interval and the second operation characteristic time interval respectively further includes: Based on the first effective operation data set, the least squares method is used to perform curve fitting between the voltage and current of the fuel cell stack, and the voltage fitting value corresponding to the first operation characteristic time interval is obtained; Based on the second effective operation data set, the least squares method is used to perform curve fitting between the voltage and current of the fuel cell stack, and the voltage fitting value corresponding to the second operation characteristic time interval is obtained.

6. A decay identification method for the operation stability of a fuel cell vehicle stack according to claim 1, characterized in that Calculating the fitting determination coefficient of the fuel cell stack for the first operation characteristic time interval and the second operation characteristic time interval based on the first effective operation data set, the second effective operation data set, and the voltage fitting values of the first operation characteristic time interval and the second operation characteristic time interval further includes: Calculating the fitting determination coefficient of the fuel cell stack for the first operation characteristic time interval based on the first effective operation data set and the voltage fitting value of the first operation characteristic time interval; Calculating the fitting determination coefficient of the fuel cell stack for the second operation characteristic time interval based on the second effective operation data set and the voltage fitting value of the second operation characteristic time interval.

7. A decay recognition method for the operating stability of a fuel cell vehicle stack according to claim 6, characterized in that, Calculating the fitting determination coefficient of the fuel cell stack for the first operation characteristic time interval based on the first effective operation data set and the voltage fitting value of the first operation characteristic time interval further includes: Calculating the average value, sum of squared residuals, and total sum of squares of the fitting voltage of the fuel cell stack for the first operation characteristic time interval based on the first effective operation data set and the voltage fitting value of the fuel cell stack for the first operation characteristic time interval; Calculating the fitting determination coefficient of the fuel cell stack for the first operation characteristic time interval based on the sum of squared residuals and total sum of squares of the fuel cell stack fitting for the first operation characteristic time interval.

8. A decay identification method for the operation stability of a fuel cell vehicle stack according to claim 6, characterized in that, Calculating the fitting determination coefficient of the fuel cell stack for the second operation characteristic time interval based on the second effective operation data set and the voltage fitting value of the second operation characteristic time interval further includes: Calculating the average value of the fitting voltage, sum of squared residuals, and total sum of squares of the fuel cell stack for the second operation characteristic time interval based on the second effective operation data set and the voltage fitting value of the fuel cell stack for the second operation characteristic time interval; Calculating the fitting determination coefficient of the fuel cell stack for the second operation characteristic time interval based on the sum of squared residuals and total sum of squares of the fuel cell stack fitting for the second operation characteristic time interval.

9. A decay recognition method for the operation stability of a fuel cell vehicle stack according to claim 1, characterized in that Calculating the relative deviation value of the fitting determination coefficient of the fuel cell stack for the first operation characteristic time interval and the second operation characteristic time interval, and determining whether the operation stability of the fuel cell stack has decayed based on the relative deviation value further includes: Comparing the relative deviation value with a set reference threshold to determine whether the operation stability of the fuel cell stack has decayed; If the relative deviation value is greater than the set reference threshold, it indicates that the operation stability of the fuel cell stack has decayed; Otherwise, it indicates that the operation stability of the fuel cell stack has not decayed.

Images