Fuel cell system operating condition detection method, automatic test method, and test system

Abstract

Disclosed in the present invention are a fuel cell system operating condition detection method, an automatic test method, and a test system. The fuel cell system operating condition detection method comprises: firstly, on the basis of main operating conditions of a fuel cell system, selecting a current, a hydrogen inlet pressure, an air inlet pressure, a coolant inlet temperature and a coolant outlet temperature as determination references for operating condition detection; then, performing interpolation on the basis of the current value of the current, so as to acquire control target values of the remaining parameters; and finally, determining a system state on the basis of signal features of the current combined with whether the remaining parameters are within threshold ranges of the control target values, so as to complete operating condition identification. The method is applicable to a fuel cell test system, and has the advantages of facilitating calculation, requiring no training, allowing online operation, involving an automatic test sequence, etc. An automatic test procedure can also avoid the problem of the next group of new test conditions being automatically triggered due to latency-induced erroneous determination during operating condition detection, thereby improving the stability and reliability of the system.

Description

Fuel cell system operating condition detection method, automated test method and test system Technical Field

[0001] The present invention relates to the field of fuel cell technology, and in particular to a fuel cell system operating condition detection method, an automated testing method and a system. Background Art

[0002] Polarization curve testing and dynamic operating condition testing of fuel cell systems require a method that can automate experimental conditions to reduce the workload of the experimenter, simplify experimental operations, and improve overall experimental efficiency. However, this task faces multiple challenges, including dynamic changes in the experimental environment, fluctuations in system state, interference from thermal radiation, and uncertainty in sensor state. As a result, the collected data often contains various noises, which may be autocorrelated or non-Gaussian. In this context, a method is needed to identify the steady-state and transient states of the test system online within the noisy process signal.

[0003] The importance of steady-state identification is self-evident. It not only serves as a key step in triggering data collection, process fault detection, and data analysis, but also serves to determine when the current experimental conditions have ended, allowing the implementation of the next set of conditions. Transient identification, on the other hand, is crucial for collecting data for dynamic modeling and determining the onset of process response. Currently, a variety of methods exist for determining system states, including Bayesian online change point detection algorithms based on probabilistic models, mean tests and t-tests based on likelihood ratio tests, kernel-space-based clustering algorithms, and even algorithms based on neural networks and big data.

[0004] Currently, existing methods have several limitations. Some require massive datasets, which is impractical for use during testing and development. Others require significant computing power, making them difficult to implement online, especially in real-time detection scenarios. Still others perform poorly when affected by noise, hindering effective functionality. Summary of the Invention

[0005] The purpose of the present invention is to overcome the shortcomings of the existing technology and provide a fuel cell system operating condition detection method, an automated test method and system, which include functions such as online operating condition detection, data storage, and automatic switching of experimental conditions, and are used to solve the problems of the existing methods such as complex experimental operations, the need to train a large amount of historical data, large amount of calculation, inability to run online, and poor robustness.

[0006] To achieve the above object, the present invention is implemented by adopting the following technical solutions:

[0007] In a first aspect, the present invention provides a method for detecting the operating condition of a fuel cell system, comprising the following steps:

[0008] Step 1: Acquire a signal measurement value of a parameter, wherein the signal measurement value of the parameter includes current signal sampling data;

[0009] Step 2: Calculate and obtain a current state estimation value based on the current signal sampling data;

[0010] Step 3: judging the stable state of the current according to the estimated value of the current state;

[0011] Step 4: Determine the fuel cell system operating conditions based on the steady state of the current.

[0012] Furthermore, current signal sampling data is obtained, including:

[0013] Collect and store the current signal data within n seconds before the current sampling time in the form of a circular linked list I={I1,I2,I3…I N}, N is the length of the sampling time window, and f is the sampling frequency.

[0014] The selection rule for the length N of the time window is:

[0015] Among them, α is the probability of type I error, and β is the probability of type II error.

[0016] Furthermore, the state estimation value of the current is calculated based on the current signal sampling data, including:

[0017] The current state estimation value ζ is calculated as follows:

[0018] Where, I i Represents the i-th current signal data point, i = 1, 2, 3…N; Represents the sum of the squares of N stored data points; Represents the sum of N stored data points; Represents the sum of the squares of the differences between two adjacent data points of the N stored data points.

[0019] Furthermore, judging the stable state of the current according to the estimated state value of the current includes:

[0020] Confirm the first type error probability α and the second type error probability β of the hypothesis test, and select the thresholds of the current state estimation value LoValue=100×α and UpValue=100×β.

[0021] When ζ>UpValue, the current is in transient state;

[0022] When ζ < LoValue, the current is in a steady state;

[0023] When LoValue < ζ < UpValue, it is considered that the current maintains its original state unchanged.

[0024] Furthermore, according to the steady state of the current, the operating conditions of the fuel cell system are determined, including:

[0025] When the current is in a transient state, the operating condition of the fuel cell system is transient.

[0026] Furthermore, the method further includes:

[0027] Obtaining the signal measurement values of other parameters; the other parameters include the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack;

[0028] Obtaining the control target values of other parameters;

[0029] Obtaining the thresholds of other parameters;

[0030] According to the signal measurement values, control target values, and thresholds of the other parameters, determining the steady state of the other parameters;

[0031] According to the steady state of the current and the steady state of the other parameters, determining the operating conditions of the fuel cell system.

[0032] Furthermore, obtaining the signal measurement values of other parameters includes:

[0033] Obtaining the signal measurement values θ of the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack through sensors i .

[0034] Where i = 1, 2, 3, 4 represents the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack respectively.

[0035] Furthermore, obtaining the control target values of other parameters includes:

[0036] Due to the strong coupling of the parameters of the fuel cell system, interpolating based on the current value of the current signal to obtain the control target values γ of the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack i ;

[0037] Where i = 1, 2, 3, 4 represents the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack respectively.

[0038] Furthermore, obtaining the thresholds of other parameters includes:

[0039] Threshold Δ i By the control accuracy ε i1 and the sensor's accuracy ε i1 Determine: Δ i =ε i1 +ε i2

[0040] Where i=1, 2, 3, and 4 represent the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack, respectively.

[0041] Furthermore, judging the stable state of other parameters based on the signal measurement value, control target value and threshold value of the other parameters includes:

[0042] When the signal measurement value θ i Satisfy the condition |θ i -γ i |≤Δ i When , the measured signal reaches a stable state;

[0043] Where i=1, 2, 3, and 4 represent the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack, respectively.

[0044] Furthermore, determining the fuel cell system operating condition based on the steady state of the current and the steady states of other parameters includes:

[0045] When the steady states of the current, hydrogen pressure entering the stack, air pressure entering the stack, coolant temperature entering the stack, and coolant temperature leaving the stack are all in steady state, the system is considered to be in a stable state; otherwise, the system is considered to be in a transient state.

[0046] In a second aspect, the present invention provides an automated test method comprising the following steps:

[0047] Obtain the steady state of current, hydrogen pressure entering the stack, air pressure entering the stack, coolant temperature entering the stack, and coolant temperature leaving the stack;

[0048] If the steady state of the current is transient, the system state value is set to 0, State=0;

[0049] If the steady state of the current is steady state, the steady states of the sampling values ​​of the inlet hydrogen pressure, inlet air pressure, inlet coolant temperature and outlet coolant temperature are also steady state, and the current system state value State=0, then the system may not be in steady state at this time. When it is detected again that it is in steady state, the system state value is set to 1, that is, State=1; in other cases, the system state value State remains unchanged.

[0050] When State = 1 and the system is determined to be in a steady state, record the parameter data at the steady state and the current steady-state duration. If the current steady-state duration is less than the predetermined steady-state time, it indicates that the current conditional experiment test does not meet the target requirements, and continue to wait for the next sampling time to repeat the test steps. If the current steady-state duration is greater than the predetermined steady-state time, it indicates that the target requirements of the current conditional experiment test are achieved, set the next experimental condition, and repeat the test steps to restart the experiment.

[0051] When State = 0 and the system is determined to be in a transient state, record the parameter data at the transient state and the current transient duration; if the current transient duration is less than the predetermined transient time, it indicates that the system is in an unstable state under the current experimental conditions, and continue to wait for the next sampling time to repeat the test steps. If the current transient duration exceeds the time limit, it indicates that the system cannot reach a steady state under the current experimental conditions, set the system state value to 1, State = 1, and set the next experimental condition, and repeat the test steps to restart the experiment.

[0052] Furthermore, obtaining the steady state of the current includes:

[0053] Collect and store the current signal data within the previous n seconds before the current sampling time in the form of a circular linked list, I = {I1, I2, I3…IN}, N = n×f, where f is the sampling frequency. N}, N = n×f, f is the sampling frequency.

[0054] Perform current state estimation. The calculation formula for the state estimation value ζ of the current is as follows:

[0055] In the formula, I i represents the i-th current signal data point, i = 1, 2, 3…N; represents the sum of the squares of the N stored data points; represents the sum of the N stored data points; represents the sum of the squares of the differences between adjacent two data points of the N stored data points.

[0056] Considering the type-I error probability α and type-II error probability β of the hypothesis test, determine the thresholds LoValue = 100×α and UpValue = 100×β of the current state estimation value.

[0057] The rule for selecting the length N of the time window is:

[0058] When ζ>UpValue, the current is in a transient state; when ζ<LoValue, the current is in a steady state; when LoValue<ζ<UpValue, there is not enough reason to reject or accept the null hypothesis, and the current remains unchanged.

[0059] Furthermore, obtaining the stable states of the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack includes:

[0060] Get the control target value γ i ,

[0061] By the control accuracy ε i1 and the sensor's accuracy ε i1 Determine the threshold Δ i : Δ i =ε i1 +ε i2 .

[0062] When the signal measurement value θ i Satisfy the condition |θ i -γ i |≤Δ i When , the measured signal reaches a stable state.

[0063] Where i=1, 2, 3, and 4 represent the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack, respectively.

[0064] In a third aspect, the present invention provides a corresponding fuel cell system testing system:

[0065] The test system includes a sensor arranged on the fuel cell system to be tested, an operating condition detection module connected to the sensor, and a controller connected to the operating condition detection module;

[0066] The sensor is used to collect signal measurement values ​​of parameters;

[0067] The operating condition detection module is used to obtain and acquire the stable state of the parameter and the operating condition of the fuel cell system to be tested based on the signal measurement value of the acquired parameter;

[0068] The controller is used to obtain and execute the method according to the second aspect based on the stable state of the parameter and the operating condition of the fuel cell system to be tested.

[0069] Compared with the prior art, the present invention has the following beneficial effects:

[0070] This method is applicable to fuel cell test systems and has the advantages of convenient calculation, no need for training, online operation, and automated experimental sequence.

[0071] The automated test process of the present invention can also avoid the problem of delayed misjudgment of working condition detection automatically triggering the next set of new experimental conditions, thereby improving the stability and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] FIG1 is a flowchart of a fuel cell system operating condition detection and automated experiment sequence;

[0073] Figure 2 is a fuel cell system test block diagram;

[0074] Figure 3 is a schematic diagram of the experimental parameters of the fuel cell system obtained according to the method described. Red marks in the figure indicate steady state (State = 1), and black marks indicate transient state (State = 0). In Figure 3, (a), (b), (c), (d), and (e) represent the parameters of the fuel cell stack current, hydrogen inlet pressure, air inlet pressure, coolant inlet temperature, and coolant outlet temperature, respectively. DETAILED DESCRIPTION

[0075] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and are not intended to limit the scope of protection of the present invention.

[0076] Example 1:

[0077] This embodiment provides a method for detecting the operating condition of a fuel cell system, which mainly includes the following steps:

[0078] Based on the fuel cell system's primary operating conditions, five parameters are selected as the basis for operating condition detection: current, hydrogen inlet pressure, air inlet pressure, coolant inlet temperature, and coolant outlet temperature. Due to the strong coupling between fuel cell system parameters, the control target values ​​for the remaining four parameters are interpolated from the current value of the current signal. Based on the characteristics of the current signal, a preliminary estimate of the system's state is made. The final determination of the system's state, or operating condition, is based on whether the remaining parameters are within the control target thresholds.

[0079] The current signal is determined as follows:

[0080] Collect and store the data within n seconds before the current sampling time in the form of a circular linked list, I={I1,I2,I3…I N}, N = n × f, f is the sampling frequency.

[0081] Taking the data in the current time window as samples,

[0082] Null hypothesis H0: The current is in a stable state.

[0083] Alternative hypothesis H1: The current is in an unsteady state.

[0084] Perform current state estimation, and the current state estimation value ζ is calculated as follows:

[0085] Where, I i Represents the i-th current signal data point, i = 1, 2, 3…N; Represents the sum of the squares of N stored data points; represents the sum of N stored data points; represents the sum of the squares of the differences between adjacent data points among the N stored data points.

[0086] When calculating the above formula, only the data of three sampling points on both sides of the position where the data is about to enter the circular linked list need to be processed.

[0087] Considering the type-I error probability α and type-II error probability β of the hypothesis test, select the thresholds LoValue = 100×α and UpValue = 100×β for the current state estimation value.

[0088] The type-I error and type-II error are two technical terms introduced corresponding to the hypothesis test. For the type-I error, its probability α is generally specified (can be taken) as 0.01 or 0.05. For the type-II error, its probability β can generally be taken as 0.2, 0.1 or 0.05. Specifically, what value to take depends on the acceptance degree of the error, and different values are taken for different problems. Figure 3 is the judgment result when α = 0.01 and β = 0.1.

[0089] Specifically for the working condition detection scenario of the present invention, when the detector has the lowest acceptance degree of the error, the type-I error probability α is taken as 0.05, and the type-II error probability β is taken as 0.1. When the detector has the highest acceptance degree of the error, the type-I error probability α is taken as 0.01, and the type-II error probability β is taken as 0.2. Generally (when the detector has no special requirements for the acceptance degree of the error), the type-I error probability α is taken as 0.01, and the type-II error probability β is taken as 0.1.

[0090] The rule for selecting the length N of the time window is:

[0091] When ζ > UpValue, reject the original hypothesis H0, that is, the current is in the transient state; when ζ < LoValue, accept the original hypothesis H0, that is, the current is in the steady state; when LoValue < ζ < UpValue, there is not enough reason to reject or accept the original hypothesis, and at this time, it is considered that the current maintains the original state unchanged.

[0092] For the remaining signals, the control target value γ i is obtained according to the set control program. The specific method for obtaining the control target values of the other four parameters by interpolating according to the current value of the current signal is:

[0093] Due to the strong coupling of the parameters of the fuel cell system, the control target values γ of the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack are obtained by interpolating according to the current value of the current signal i ;

[0094] Maintaining the healthy and continuous operation of the fuel cell stack requires consideration of its operating conditions. Polarization curves and the limits provided by the stack supplier are typically used as references, with system manufacturers also calibrating their own parameters. Each current value corresponds to a set of operating conditions, and selection is typically done using a table lookup, with linear interpolation being the most common method.

[0095] Threshold Δ i By the control accuracy ε i1 and the sensor's accuracy ε i1 Determine, that is: Δ i =ε i1 +ε i2 When the signal measurement value θ i Satisfy the condition |θ i -γ i |≤Δ i When , the measured signal reaches a stable state. Here i represents the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack.

[0096] When the current, hydrogen inlet pressure, air inlet pressure, coolant inlet temperature, and coolant outlet temperature are all in steady state, the system is considered to be in a stable state. The rest of the cases are unsteady state, that is, transient.

[0097] Example 2:

[0098] This embodiment provides an automated test method, as shown in FIG1 , and the specific steps are as follows:

[0099] For fuel cell systems, due to the response hysteresis of various components, when the experimental conditions are changed, the measurement signal usually does not change immediately, and may remain in a steady state for a very short time before the measurement signal represents the change. In order to prevent the operating condition detection from being misjudged due to the delay when changing a new set of experimental conditions and automatically triggering the next set of new experimental conditions, the automation algorithm should start the next set of experimental conditions after detecting that it is in a steady state again after passing a state that may not be in a steady state. The logic applied to the experimental sequence automation method is as follows:

[0100] The sampling data is obtained and the state estimation value ζ of the current is calculated. If the estimation value ζ meets the transient criterion, the system state value is set to 0, that is, State = 0; if the estimation value ζ meets the steady-state criterion, the sampling values ​​of the inlet hydrogen pressure, inlet air pressure, inlet coolant temperature and outlet coolant temperature are also in a steady state, and the current system state value State = 0, then the system may not be in a steady state at this time. If it is detected to be in a steady state again, the system state value is set to 1, that is, State = 1; in other cases, the system state value State remains unchanged.

[0101] When State = 1, meaning the system is in steady state, record the parameter data and the current steady state duration. If the current steady state duration is less than the predetermined steady state time, meaning the current conditional test has not met the target requirements, wait for the next sampling time. If the current steady state duration is greater than the predetermined steady state time, meaning the current conditional test has met the target requirements, set the next experimental condition, and continue the experiment.

[0102] When State = 0, meaning the system is in a transient state, record the transient parameter data and the current transient duration. If the current transient duration is less than the predetermined transient time, meaning the system is in an unstable state under the current experimental conditions, wait for the next sampling time. If the current transient duration exceeds the time limit, meaning the system cannot reach a steady state under the current experimental conditions, set the system state value to 1, i.e., State = 1, set the next experimental conditions, and continue the experiment.

[0103] The method for determining whether the stable state of the five parameters of current, hydrogen inlet pressure, air inlet pressure, coolant inlet temperature, and coolant outlet temperature is transient or steady is as described in the first embodiment.

[0104] A schematic diagram of the experimental parameters of the fuel cell system obtained according to the above method is shown in FIG3 , where the red mark indicates the steady state (State=1) and the black mark indicates the transient state (State=0).

[0105] Figure 3 is divided into five sub-graphs: sub-graphs (a), (b), (c), (d), and (e) represent the parameter values ​​of the fuel cell stack current, hydrogen inlet pressure, air inlet pressure, coolant inlet temperature, and coolant outlet temperature, respectively.

[0106] Example 3:

[0107] To apply the above-mentioned automated experimental method, this embodiment proposes a corresponding fuel cell system testing system, as shown in FIG2 . The testing system includes a sensor disposed on the fuel cell system to be tested, an operating condition detection module connected to the sensor, and a controller connected to the operating condition detection module.

[0108] The sensor is used to collect signal measurement values ​​of parameters;

[0109] The operating condition detection module is used to obtain and acquire the stable state of the parameter and the operating condition of the fuel cell system to be tested based on the signal measurement value of the acquired parameter;

[0110] The controller is used to obtain and execute the method described in the second embodiment based on the stable state of the parameter and the operating condition of the fuel cell system to be tested.

[0111] The test system includes all components of the fuel cell system and at least the sensors required by the controller. After DC-DC conversion, it is connected to the electronic load. CAN bus communication is used to achieve communication between the fuel cell system components, the controller, and the host computer.

[0112] The automated experiment program identifies the system status through the working condition detection module and controls the controller to achieve the corresponding experimental conditions according to the preset experimental sequence. The data storage module is responsible for storing steady-state and transient data.

[0113] In particular, when the test system is just powered on, the battery stack is not working. At this time, the operating condition detection module can identify the working status of each sensor and automatically calibrate or warn of sensor failure.

[0114] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0115] The present application is described with reference to the flow chart and / or block diagram of the method, device (system), and computer program product according to the embodiment of the present application. It should be understood that each flow process and / or box in the flow chart and / or block diagram and the combination of the flow process and / or box in the flow chart and / or block diagram can be realized by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processing machine or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for realizing the function specified in one flow chart flow or multiple flows and / or one box or multiple boxes of the block diagram.

[0116] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0118] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for detecting the operating condition of a fuel cell system, characterized in that: Comprising the following steps: Obtain the signal measurement value of a parameter, where the signal measurement value of the parameter includes current signal sampling data; Calculate the state estimation value of the current based on the current signal sampling data; Judge the stable state of the current according to the state estimation value of the current, and the stable state of the current is used to determine the operating condition of the fuel cell system; Wherein, determining the operating condition of the fuel cell system includes: When the current is in a transient state, the operating condition of the fuel cell system is transient; Calculating the state estimation value of the current according to the current signal sampling data includes: The current state estimation value ζ is calculated as follows: Where, I i Represents the i-th current signal data point, i = 1, 2, 3…N; Represents the sum of the squares of N stored data points; Represents the sum of N stored data points; Represent the sum of the squares of the differences between adjacent two of the N stored data points.

2. The fuel cell system operating condition detection method according to claim 1, characterized in that: Obtaining the current signal sampling data includes: Collect and store the current signal data within n seconds before the current sampling time in the form of a circular linked list I={I1,I2,I3…I N }, N is the length of the sampling time window, f is the sampling frequency; The selection rule for the length N of the time window is: Where α is the type I error probability, β is the type II error probability, s represents seconds, and 1s represents 1 second.

3. The fuel cell system operating condition detection method according to claim 2, characterized in that: Judging the stable state of the current according to the state estimation value of the current includes: Confirm the type I error probability α and type II error probability β of the hypothesis test, and select the lower threshold LoValue = 100×α and upper threshold UpValue = 100×β of the current state estimation value ζ; When ζ>UpValue, the current is in a transient state; When ζ<LoValue, the current is in a steady state; When LoValue<ζ<UpValue, it is considered that the current maintains its original state unchanged.

4. The fuel cell system operating condition detection method according to claim 1, characterized in that: The method further includes: Obtain the signal measurement values of other parameters; the other parameters include the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack; Obtain the control target values of other parameters; Obtain the thresholds of other parameters; Judge the stable states of other parameters according to the signal measurement values, control target values and thresholds of other parameters; Determine the operating condition of the fuel cell system according to the stable state of the current and the stable states of other parameters.

5. [Corrected 27.04.2025 according to Rule 26] The method for detecting the operating condition of a fuel cell system according to claim 4, characterized in that: Obtaining the signal measurement values of other parameters includes: The sensor obtains the signal measurement values ​​θ of the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack. i ; Where i = 1, 2, 3, 4 respectively represent the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack.

6. The fuel cell system operating condition detection method according to claim 4, characterized in that: Obtaining the control target values of other parameters includes: Due to the strong coupling of various parameters of the fuel cell system, the control target values ​​γ of the inlet hydrogen pressure, inlet air pressure, inlet coolant temperature and outlet coolant temperature are obtained by interpolation based on the current value of the current signal. i ; Where i = 1, 2, 3, 4 respectively represent the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack.

7. The fuel cell system operating condition detection method according to claim 4, characterized in that: Obtaining the thresholds of other parameters includes: Threshold Δ i By the control accuracy ε i1 and the sensor's accuracy ε i1 Determine: Δ i =ε i1 +ε i2 Where i = 1, 2, 3, 4 respectively represent the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack.

8. The fuel cell system operating condition detection method according to claim 4, characterized in that: Judging the stable states of other parameters according to the signal measurement values, control target values and thresholds of other parameters includes: When the signal measurement value θ i Satisfy the condition |θ i -γ i |≤Δ i When , the measured signal reaches a stable state; Where i = 1, 2, 3, 4 respectively represent the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack.

9. The fuel cell system operating condition detection method according to claim 4, characterized in that: Determining the operating condition of the fuel cell system according to the stable state of the current and the stable states of other parameters includes: When the stable states of the current, the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack are all in a steady state, it is considered that the system is in a stable state, otherwise it is considered that the system is in a transient state.

10. An automated test method, characterized in that: Comprising the following steps: Obtain the stable states of the current, the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack; If the steady state of the current is transient, set the system state value to 0, State = 0; If the steady state of the current is steady state, and the steady states of the sampled values of the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack are also in steady state, and the current system state value State = 0, then at this time, the system has passed the state that may not be in steady state and is detected to be in steady state again, and the system state value State is set to 1, State = 1; in other cases, the system state value State remains unchanged; When State = 1 and the system determines it is in steady state, record the parameter data at steady state and the current steady state duration; If the current steady state duration is less than the predetermined steady state time, it means that the current conditional experiment test does not meet the target requirements, and continue to wait for the next sampling time to repeat the test steps; if the current steady state duration is greater than the predetermined steady state time, it means that the target requirements of the current conditional experiment test are achieved, set the next experimental condition, and repeat the test steps to start the test again; When State = 0 and the system determines it is in transient state, record the parameter data at transient state and the current transient duration; If the current transient duration is less than the predetermined transient time, it means that the system is in an unstable state under the current experimental conditions, and continue to wait for the next sampling time to repeat the test steps; if the current transient duration exceeds the time limit, it means that the system cannot reach the steady state under the current experimental conditions, set the system state value to 1, State = 1, and set the next experimental condition, and repeat the test steps to start the test again.

11. The automated testing method according to claim 10, wherein: Obtain the steady state of the current, including: Collect and store the current signal data within n seconds before the current sampling time in the form of a circular linked list, I={I1,I2,I3…I M }, N = n × f, f is the sampling frequency; Perform current state estimation, and the current state estimation value ζ is calculated as follows: Where, I i Represents the i-th current signal data point, i = 1, 2, 3…N; Represents the sum of the squares of N stored data points; Represents the sum of N stored data points; It represents the sum of the squares of the differences between adjacent two of the N stored data points; Considering the first type error probability α and the second type error probability β of the hypothesis test, determine the threshold values of the current state estimate LoValue = 100×α and UpValue = 100×β; The selection rule for the length N of the time window is: When ζ>UpValue, the current is in transient state; when ζ<LoValue, the current is in steady state; when LoValue<ζ<UpValue, there is not enough reason to reject or accept the original hypothesis, and the current remains unchanged in its original state.

12. The automated testing method according to claim 10, wherein: Obtain the steady states of the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack, including: Get the control target value γ i , By the control accuracy ε i1 and the sensor's accuracy ε i1 Determine the threshold Δ i :Δ i =ε i1 +ε i2 ; When the signal measurement value θ i Satisfy the condition |θ i -γ i |≤Δ i When , the measured signal reaches a stable state; When i = 1, 2, 3, 4, they respectively represent the hydrogen pressure entering the stack, the air pressure entering the stack, the coolant temperature entering the stack, and the coolant temperature leaving the stack.

13. A fuel cell system testing system, characterized in that: The test system includes sensors arranged on the fuel cell system to be tested, a working condition detection module connected to the sensors, and a controller connected to the working condition detection module; The sensors are used to collect the signal measurement values of the parameters; The working condition detection module is used to obtain and obtain the steady state of the parameters and the working conditions of the fuel cell system to be tested based on the signal measurement values of the collected parameters; The controller is used to obtain and execute the method according to any one of claims 10 - 12 based on the steady state of the parameters and the working conditions of the fuel cell system to be tested.

Images