Method for detecting fault of fuel cell system and related device

Abstract

The invention relates to a method for detecting a fault of a fuel cell system and a related device. The method includes acquiring a current signal of a hydrogen circulation pump in the fuel cell system. The method further includes generating a target signal based on the current signal and a predetermined reference signal, where a frequency of the predetermined reference signal corresponds to a predetermined fault of the fuel cell system. Further, the method includes determining a fault condition of the fuel cell system based on the target signal. Through the mode, the fault state related to the hydrogen insufficiency of the fuel cell system can be detected on the basis of the current signal of the hydrogen circulating pump, and an alarm can be provided before the hydrogen insufficiency of the fuel cell system occurs on the basis. Therefore, the membrane electrode can be prevented from being damaged, so that the robustness of the fuel cell system can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of fuel cell technology, and more particularly, to a method and related apparatus for detecting failures in a fuel cell system. Background Art

[0002] In a fuel cell system, hydrogen and oxygen undergo an electrochemical reaction on the membrane electrode of the fuel cell stack to generate electricity. This process is usually accompanied by the generation of water at the cathode. Most of the water in the cathode of the fuel cell stack is discharged through the air outlet of the cathode circuit, and a part of it will penetrate from the cathode to the anode through the membrane electrode, causing liquid water to appear in the anode. Too much liquid water in the anode will cause anode flooding, that is, too much liquid water will block the gas diffusion layer or catalyst layer of the membrane electrode. In some cases, nitrogen in the cathode of the fuel cell stack will also penetrate through the membrane electrode to the anode. This nitrogen will dilute the hydrogen in the anode, reducing the hydrogen concentration in the anode.

[0003] Anode flooding or low hydrogen concentration at the anode may result in less hydrogen than required for the electrochemical reaction on the membrane electrode, a condition known as hydrogen starvation. In the case of hydrogen starvation, the hydrogen participating in the electrochemical reaction on the membrane electrode is insufficient to support the fuel cell stack's output. In this case, the membrane electrode itself may participate in the reaction, resulting in damage to the membrane electrode and, in turn, inability to operate the fuel cell system properly. Summary of the Invention

[0004] Embodiments of the present disclosure provide a method and related apparatus for detecting a fuel cell system fault. In a first aspect of the present disclosure, a method for detecting a fuel cell system fault is provided. The method includes acquiring a current signal from a hydrogen circulation pump in the fuel cell system. The method also includes generating a target signal based on the current signal and a predetermined reference signal, wherein the frequency of the predetermined reference signal corresponds to a predetermined fuel cell system fault. Furthermore, the method also includes determining a fuel cell system fault state based on the target signal.

[0005] In a second aspect of the present disclosure, a device is provided. The device includes an acquisition unit configured to acquire a current signal of a hydrogen circulation pump in a fuel cell system. The device also includes a signal conversion unit configured to generate a target signal based on the current signal and a predetermined reference signal, wherein the frequency of the predetermined reference signal corresponds to a predetermined fault of the fuel cell system. The device also includes a fault determination unit configured to determine a fault state of the fuel cell system based on the target signal.

[0006] In a third aspect of the present disclosure, a controller is provided. The controller includes one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, causes the one or more processors to implement the method provided according to the first aspect of the present disclosure.

[0007] In a fourth aspect of the present disclosure, a fuel cell system is provided, comprising the controller provided according to the third aspect of the present disclosure.

[0008] In a fifth aspect of the present disclosure, a machine-readable storage medium is provided, wherein the machine-readable storage medium stores machine-executable instructions, wherein the machine-executable instructions are executed by a processor to implement the method provided according to the first aspect of the present disclosure.

[0009] In a sixth aspect of the present disclosure, a program product is provided, which is tangibly stored on a non-volatile, machine-readable medium and includes machine-executable instructions that, when executed, cause a machine to perform the method provided according to the first aspect of the present disclosure.

[0010] It should be understood that the contents described in the Summary of the Invention section are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0012] Figure 1 shows a schematic diagram of a fuel cell system in which various embodiments of the present disclosure may be implemented;

[0013] Figure 2 A flow chart illustrating a method for detecting a fault in a fuel cell system according to some embodiments of the present disclosure is shown;

[0014] Figure 3A shows a schematic diagram of a current signal according to some embodiments of the present disclosure;

[0015] Figure 3B A schematic diagram illustrating a predetermined reference signal according to some embodiments of the present disclosure is shown;

[0016] Figure 3C A schematic diagram illustrating a target signal according to some embodiments of the present disclosure is shown;

[0017] Figure 4A schematic diagram showing a corresponding relationship between the magnitude of an integral value and a fault state according to some embodiments of the present disclosure;

[0018] Figure 5 A schematic flow chart illustrating a method for detecting flooding of a fuel cell system according to some embodiments of the present disclosure is shown;

[0019] Figure 6 A schematic flow chart illustrating a method for detecting a nitrogen state of a fuel cell system according to some embodiments of the present disclosure is shown;

[0020] Figure 7 A block diagram illustrating an apparatus for detecting a fault in a fuel cell system according to some embodiments of the present disclosure; and

[0021] Figure 8 A block diagram of a device in which various embodiments of the present disclosure may be implemented is shown. DETAILED DESCRIPTION

[0022] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0023] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to." The term "based on" should be understood as "based at least in part on." The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment." The terms "first," "second," etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0024] As mentioned above, the fuel cell stack may be short of hydrogen (also known as hydrogen starvation or hydrogen deficiency) due to flooding or nitrogen penetration, which may damage the membrane electrode of the fuel cell stack. In order to ensure the normal operation of the fuel cell system, it is necessary to identify hydrogen deficiency in a timely manner. In the related art, the detection of hydrogen deficiency is carried out by means of a single-chip voltage monitor (CVM). CVM can determine whether the fuel cell stack is short of hydrogen by the voltage change output by the fuel cell stack. However, the cost of configuring CVM in the fuel cell system is very high, and CVM detects the problem of hydrogen deficiency that has already occurred, and cannot provide an early warning before the hydrogen deficiency occurs. In other words, CVM provides a hydrogen deficiency detection result after the fuel cell stack has hydrogen deficiency. This hydrogen deficiency has already occurred, which means that the membrane electrode of the fuel cell stack has been damaged. At present, there is still a lack of a method that can provide an early warning before hydrogen deficiency occurs.

[0025] The researchers of this application found that since the hydrogen circulation pump in the fuel cell system runs at a fixed speed, when the water in the anode increases or the nitrogen concentration increases, the resistance encountered by the blades of the hydrogen circulation pump will change. In order to maintain the speed, the hydrogen circulation pump will adjust the output power accordingly. In this process, the current signal of the hydrogen circulation pump will also change. On this basis, the embodiment of the present disclosure proposes a scheme for detecting faults in the fuel cell system. In the embodiment of the present disclosure, the current signal of the hydrogen circulation pump in the fuel cell system can be obtained, and a target signal can be obtained based on the current signal and a predetermined reference signal corresponding to a predetermined fault of the fuel cell system, and the fault state of the fuel cell system can be determined based on the target signal.

[0026] In this way, the water content and / or nitrogen concentration in the anode circuit of the fuel cell system can be analyzed based on the current signal of the hydrogen circulation pump, thereby enabling the detection of fault conditions and the prediction of possible hydrogen shortages. In this way, the fault condition of the fuel cell system can be determined before hydrogen deficiency causes damage to the membrane electrode, and timely measures can be taken to prevent damage to the membrane electrode, thereby improving the robustness of the fuel cell system during operation.

[0027] Figure 1 Schematic diagram of a fuel cell system 100 in which various embodiments of the present disclosure may be implemented is shown. Figure 1The fuel cell system 100 may include a fuel cell stack 101. The fuel cell stack 101 may include a cathode 102, an anode 103, and a membrane electrode 104. The oxygen in the cathode 102 and the hydrogen in the anode 103 may undergo an electrochemical reaction on the membrane electrode 104 to generate electrical energy. The fuel cell system 100 may also include a direct current / direct current (DC / DC) converter 120. The DC / DC converter 120 may adjust the voltage and current output by the fuel cell stack 101 and may convert the varying voltage provided by the fuel cell stack 101 into a stable output voltage. It should be understood that Figure 1 The fuel cell stack 101 is shown for illustration purposes only. In some embodiments, the fuel cell stack 101 may include a plurality of monolithic cells connected in series, each of which may include a cathode, an anode, and a membrane electrode.

[0028] The fuel cell system 100 may further include a hydrogen injector 105, a water separator 106, a hydrogen circulation pump 107, a drain valve 108 and a hydrogen discharge valve 109. The hydrogen injector may supply the hydrogen in the hydrogen storage system to the anode 103 and control the pressure and flow of the hydrogen. The water separator 106 may separate the liquid water in the gas at the anode 103 gas outlet and discharge the liquid water through the drain valve 108. The hydrogen discharge valve 109 may also be referred to as a purge valve, which may discharge the impurity gas (e.g., nitrogen) when the concentration of the impurity gas in the anode 103 becomes high. The hydrogen circulation pump 107 may circulate the unreacted hydrogen at the gas outlet of the anode 103 to the air inlet of the anode 103.

[0029] The fuel cell system 100 may also include a filter 110, an air compressor 111, an intercooler 112, an upstream shutoff valve 113, an exhaust throttle valve 114, a bypass valve 115, and an exhaust muffler 116. The filter 110, which can be referred to as an air cleaner, filters particulate matter from the air to prevent clogging of the fuel cell system 100's pipelines. The air compressor 111 pressurizes air to provide air to the cathode 102 of the fuel cell stack 101. The intercooler 112 cools the compressed air provided by the air compressor 111. The upstream shutoff valve 113 is open when the fuel cell system 100 is operating and closed when the fuel cell system 100 is shut down. The exhaust throttle valve 114 discharges reacted cathode gas and regulates the gas pressure at the cathode 102 outlet and the flow rate of gas supplied to the fuel cell stack 101. The bypass valve 115 can be opened when the upstream shutoff valve 113 is closed to discharge air provided by the air compressor 111. The tail exhaust muffler 116 can reduce the noise generated by exhaust from the fuel cell system 100 .

[0030] In the fuel cell system 100, the hydrogen injector 105, the water separator 106, the hydrogen circulation pump 107, the drain valve 108, the hydrogen exhaust valve 109, and the anode 103 can be connected by pipes, and together constitute the anode subsystem (also called the anode loop) in the fuel cell system 100. The filter 110, the air compressor 111, the intercooler 112, the upstream shut-off valve 113, the exhaust throttle valve 114, the bypass valve 115 and the cathode 102 are connected by pipes, and together constitute the cathode subsystem (also called the cathode loop) in the fuel cell system 100. In the fuel cell system 100, the water and exhaust gas discharged from the anode subsystem and the exhaust gas discharged from the cathode subsystem can be discharged from the fuel cell system 100 through the tail exhaust. Figure 1 The flow direction of the pipeline and the gas or liquid in the pipeline is indicated by arrows.

[0031] The fuel cell system 100 may also include a fuel cell control unit (FCCU) 130. FCCU 130 can control various components within the fuel cell system 100, achieving overall control of the fuel cell system, including hydrogen and air management, energy conversion and monitoring, fault diagnosis and handling, and communication with other systems. In some embodiments, FCCU 130 can obtain a current signal from the hydrogen circulation pump 107 and determine a fault state of the fuel cell system 100 based on the current signal.

[0032] In some embodiments, the FCCU 130 may adjust the opening frequency of the drain valve 108 if it determines that there is excessive moisture in the anode circuit based on the current signal of the hydrogen circulation pump 107. In some embodiments, the FCCU 130 may adjust the opening frequency of the hydrogen drain valve 109 if it determines that the nitrogen concentration in the anode circuit is too high based on the current signal of the hydrogen circulation pump 107. In some embodiments, the FCCU 130 may control the fuel cell system 100 to shut down if it determines that there is a risk of hydrogen deficiency in the fuel cell system 100.

[0033] It should be understood that Figure 1The fuel cell system 100 shown is only an example of an embodiment of the present disclosure and does not limit the embodiments of the present disclosure. For example, in some embodiments, the oxidizing gas of the cathode 102 in the fuel cell system 100 may be other types of gases, such as oxygen, and in some embodiments, the fuel gas of the anode 103 may be other types of gases, such as methanol. In the embodiments of the present disclosure, the names of the components in the fuel cell system 100 are only examples. In some embodiments, components with the same or similar functions may have different names. In some embodiments, the fuel cell system 100 may also include more or fewer components, for example, it may also include a pressure sensor for detecting pressure and a temperature sensor for detecting temperature. It should also be understood that the solutions provided in the embodiments of the present disclosure may also be applied to other types of fuel cell systems. The fuel cell system in the embodiments of the present disclosure may be applied to various scenarios and may be configured as a power source or auxiliary power in various devices, including but not limited to vehicles, yachts, aerospace equipment, underwater power equipment, etc.

[0034] Figure 2 A flow chart of a method 200 for detecting a fuel cell system fault according to some embodiments of the present disclosure is shown. The method 200 can be performed by a device for detecting a fuel cell system fault, which can be configured in the fuel cell system or can be a device independent of the fuel cell system, including but not limited to a processor, a computer, a chip, a chip system, or a server, etc. The device can also be implemented in software and / or hardware. In some embodiments, the device can be a controller in the fuel cell system, for example, Figure 1 For the sake of convenience, the method 200 will be described below with the controller as the execution subject. Figure 2 As shown, method 200 may include blocks 202 through 206 .

[0035] In box 202, the controller obtains the current signal of the hydrogen circulation pump in the fuel cell system. During the operation of the fuel cell system, the hydrogen circulation pump can recycle the unreacted hydrogen in the stack to the inlet of the anode to improve the utilization rate of the hydrogen. At the same time, the hydrogen circulation pump can also circulate a portion of the water that permeates from the cathode to the anode to the inlet of the anode. In the fuel cell system, the blades of the hydrogen circulation pump are usually set to run at a fixed speed. Since the gas composition in the anode loop will continue to change due to nitrogen permeation and water permeation, the resistance to the blades of the hydrogen circulation pump will continue to change. In order to maintain the rotational speed of the blades, the output power of the hydrogen circulation pump will continue to change. When the voltage is constant, the output current of the hydrogen circulation pump will fluctuate over time.

[0036] In some embodiments, the controller can obtain a current signal indicating the time-varying output current of the hydrogen circulation pump from a motor controller of the hydrogen circulation pump. The controller can also obtain and record the magnitude of the output current of the hydrogen circulation pump in real time, thereby forming a current signal indicating the time-varying current. In some embodiments, the controller can obtain the current signal of the hydrogen circulation pump from another device for detecting current magnitude, such as a current sensor.

[0037] In box 204, the controller generates a target signal based on the current signal and the predetermined reference signal. During the operation of the fuel cell system, due to changes in the composition of the gas in the anode loop, the current signal of the hydrogen circulation pump is the fluctuation of the current over time. This fluctuation can be regarded as the superposition of waves of multiple frequencies. The water or nitrogen in the anode loop can cause fluctuations of a specific frequency in the current signal. The frequency of the predetermined reference signal corresponds to a predetermined fault of the fuel cell system. For example, the predetermined fault can be a flooding fault caused by excessive water infiltration into the anode, or a high nitrogen concentration fault caused by excessive nitrogen infiltration into the anode. In other words, the predetermined reference signal can reflect fluctuations in the current signal related to water or fluctuations related to nitrogen concentration.

[0038] In some embodiments, the controller can decompose a wave of a specific frequency from the current signal of the hydrogen circulation pump based on a predetermined reference signal. For example, the controller can determine the wave corresponding to the frequency of the predetermined reference signal in the current signal by Fourier series expansion, and use it as the target signal. In some embodiments, the controller can multiply the current signal by the predetermined reference signal to obtain a target signal, which can reflect information related to the frequency of the predetermined reference signal in the current signal. Exemplarily, the wave function corresponding to the current signal can be, for example, s(t), and the wave function corresponding to the predetermined reference signal can be, for example, w(t), then the wave function corresponding to the target signal can be F(t)=s(t)·w(t).

[0039] In block 206, the controller determines a fuel cell system fault state based on the target signal. The target signal is generated based on a predetermined reference signal and the current signal. The target signal carries information related to the frequency of the predetermined reference signal in the current signal, that is, information related to a fuel cell system fault. Therefore, the fuel cell system fault state can be determined based on the target signal.

[0040] In some embodiments, the target signal is the result of multiplying the current signal by a predetermined reference signal. The controller can determine the fault state of the fuel cell system by determining the integral value of the target signal over time. In some embodiments, the controller can determine the fault state based on whether the integral value is zero. If the integral value is zero, it indicates that the current signal is orthogonal to the predetermined reference signal, and the current signal does not have the same frequency as the predetermined reference signal, that is, it can be determined that there is no predetermined fault in the fuel cell system. If the integral value of the target signal over time is greater than zero, it indicates that the current signal has the same frequency as the predetermined reference signal, that is, a predetermined fault may occur in the fuel cell system. In some embodiments, the controller can determine the fault state of the fuel cell system based on the size of the integral value.

[0041] In some embodiments, the target signal is a decomposition result of the current signal and is a wave in the current signal, determined by the controller to have the same frequency as a predetermined reference signal. The controller can determine a fuel cell system fault condition based on the amplitude of the target signal. In some embodiments, if the amplitude of the target signal is non-zero, it indicates that a wave with the same frequency as the predetermined reference signal is present in the current signal, indicating that a predetermined fault may have occurred in the fuel cell system. In some embodiments, if the amplitude of the target signal is zero, it indicates that a wave with the same frequency as the predetermined reference signal is not present in the current signal, indicating that the predetermined fault has not occurred in the fuel cell system.

[0042] Through the above technical solution, the fault state of the fuel cell system can be determined based on the wave of the frequency corresponding to the fault in the current signal, such as the water flooding or nitrogen concentration of the anode. Water flooding or excessive nitrogen concentration at the anode may cause insufficient hydrogen in the fuel cell stack, thereby damaging the membrane electrode. However, through the solution provided by the embodiment of the present disclosure, water flooding at the anode or excessive nitrogen concentration at the anode can be detected in time, and an alarm can be issued in time. In this way, measures can be taken in time before the membrane electrode is damaged, thereby avoiding damage to the membrane electrode. In this way, the stability of the fuel cell system can be improved. In addition, the above technical solution is based on the output current of the hydrogen circulation pump for detection. In this way, the detection of water flooding or nitrogen can be achieved without the help of CVM, which can avoid the configuration of CVM in the fuel cell system, save costs and improve efficiency.

[0043] In some embodiments, the frequency of the predetermined reference signal can be determined by a controller. In some embodiments, the controller can obtain a fault current signal when a predetermined fault occurs in the fuel cell system. The controller can perform a short-time Fourier transform or a wavelet transform on the current signal to determine the frequency corresponding to the predetermined fault. In some embodiments, based on multiple fault current signals corresponding to a specific predetermined fault, the controller can determine the frequency multiple times through a short-time Fourier transform or a wavelet transform within the time period when the predetermined fault occurs, thereby more accurately determining the frequency corresponding to the predetermined fault. In some embodiments, the controller can generate a predetermined reference signal based on the frequency. In some embodiments, the predetermined reference signal can be obtained by the controller or pre-stored in a memory configured by the controller.

[0044] Different frequencies of the predetermined reference signal can correspond to different fault conditions. In some embodiments, the controller can generate multiple target signals based on multiple predetermined reference signals of different frequencies, and use these signals to determine the type of fault in the fuel cell system. In this way, the type of fault can be identified, and if multiple faults occur, they can be identified simultaneously. This can result in more accurate and diverse detection results.

[0045] In some embodiments, in the aforementioned box 204, the controller can intercept the signal in the current signal within a specific time window, multiply it with a predetermined reference signal, and thus obtain a target signal within the predetermined time window. In some embodiments, the predetermined reference signal is a wavelet basis signal within a predetermined time window, and the controller can multiply it with the current signal to obtain a target signal within the predetermined time window. In this way, the information carried by the current signal within a specific time period can be obtained. By moving the time window, the information carried by the current signal in different time windows can be obtained, and on this basis, the fault state of the fuel cell system at different times can be determined. In this way, the fault detection result can include more information. In some embodiments, the controller can generate a target signal based on the time window in which the current moment is located, so that real-time detection of the fault state can be achieved.

[0046] For example, Figure 3A Schematic diagram showing a current signal 310 in some embodiments of the present disclosure, Figure 3B FIG. 3 is a schematic diagram showing a predetermined reference signal 320 in some embodiments of the present disclosure, Figure 3C A schematic diagram of a target signal 330 in some embodiments of the present disclosure is shown. Figure 3A The wave function corresponding to the current signal 310 in can be, for example, s(t), Figure 3BThe predetermined reference signal 320 is a wavelet basis signal, and the corresponding wave function may be, for example, w(t). The frequency of the wavelet basis signal may correspond to the predetermined fault, and the time window of the wavelet basis signal is t1 to t2. Outside the time range of t1 to t2, the value of the wavelet basis signal is zero. Figure 3C The target signal 330 in is the product of the current signal 310 and the predetermined reference signal 320, and the corresponding wave function may be F(t)=s(t)·w(t). The target signal 320 indicates information related to the frequency of the predetermined reference signal 320 in the current signal 310 within the time window t1 to t2. It should be understood that Figure 3A 、 Figure 3B and Figure 3C The current signal, the predetermined reference signal, and the target signal obtained based on the current signal and the predetermined sharp turn signal shown in the figure are merely examples of the embodiment of the present disclosure and cannot be a limitation to the embodiment of the present disclosure.

[0047] In some embodiments, the target signal is the result of multiplying the current signal by a predetermined reference signal. In the aforementioned block 206, the controller determines the fault state of the fuel cell system based on the magnitude of the integral value of the target signal. Different magnitudes of the integral value may correspond to different fault states. For example, Figure 4 A schematic diagram showing a corresponding relationship 400 between the magnitude of the integral value and the fault state in some embodiments of the present disclosure is shown. Figure 4 In the figure, the vertical axis represents the magnitude of the integral value. If the integral value is less than N1, it indicates that the fuel cell system is in a normal state. If the integral value is between N1 and N2, it indicates that the fuel cell system is in an abnormal state, but this abnormal state can be eliminated by adjusting the fuel cell system. If the integral value is greater than N2, it indicates that the fuel cell system is in a fault state, which cannot be eliminated by normal adjustment. In this way, different fault states of the fuel cell system can be determined, and different processing strategies can be implemented based on different fault states, thereby making the detection and processing of fuel cell system faults more flexible.

[0048] In some embodiments, the predetermined fault may be a flooding fault, and the controller may determine different degrees of flooding based on different integral values. For example, if the integral value is less than a predefined first integral threshold, the controller may determine that the water content in the anode circuit of the fuel cell system is within a normal water content range; if the integral value is within a predefined range between the first integral threshold and a second integral threshold, the controller may determine that the water content in the anode circuit of the fuel cell system exceeds the normal water content range, but a flooding fault has not occurred; if the integral value is greater than a predefined second integral threshold, the controller may determine that a flooding fault has occurred in the fuel cell system.

[0049] In some embodiments, the controller can obtain the efficiency of the water separator in the fuel cell system and determine the first integral threshold and the second integral threshold based on the efficiency of the water separator. For example, if the water separator is highly efficient and can promptly separate the excess water in the anode circuit, a higher first integral threshold and a higher second integral threshold can be determined. For another example, if the water separator is less efficient and cannot promptly separate the excess water in the anode circuit, a lower first integral threshold and a lower second integral threshold can be determined. In this way, the fault detection strategy can be adjusted in combination with the actual situation of the fuel cell system, thereby making the detection results more accurate.

[0050] In some embodiments, the predetermined fault may be a high nitrogen concentration fault, and the controller may determine different nitrogen concentration conditions based on different integral values. For example, if the integral value is less than a predefined third integral threshold, the controller may determine that the nitrogen concentration in the anode circuit of the fuel cell system is within a normal nitrogen concentration range; if the integral value is within a predefined range between the third integral threshold and a fourth integral threshold, the controller may determine that the nitrogen concentration in the anode circuit of the fuel cell system exceeds the normal nitrogen concentration range, but a high nitrogen concentration fault has not occurred; and if the integral value is greater than a predefined fourth integral threshold, the controller may determine that a high nitrogen concentration fault has occurred in the fuel cell system.

[0051] It should be understood that the above content is combined with Figure 4 The description of the correspondence between the integral value and the fault state is merely an example and does not limit the solutions provided by this disclosure. In some embodiments, different integral values ​​may correspond to a wider range of fault states. In some embodiments, the integral thresholds corresponding to different faults may be different. For example, the first integral threshold and the third integral threshold may be different, and the second integral threshold and the fourth integral threshold may be different.

[0052] In some embodiments, the controller can determine the fault status of the fuel cell system based on the results of multiple detections of the same fault. In some embodiments, the controller can intercept multiple time windows from the current signal and multiply them by a predetermined reference signal to obtain multiple target signals corresponding to the multiple time windows. In some embodiments, the controller can multiply the wavelet basis signals corresponding to the multiple time windows by the current signal to generate multiple target signals corresponding to the multiple time windows.

[0053] The controller may integrate the multiple target signals within their respective corresponding time windows to obtain multiple integral values, each of which may correspond to a different time window. The controller may determine a fault state of the fuel cell system based on these integral values. For example, if the number of integral values ​​greater than a predetermined threshold among these integral values ​​is greater than or equal to a predetermined threshold, the controller may determine that a predetermined fault has occurred in the fuel cell system. For example, if the number of integral values ​​greater than the predetermined threshold among these integral values ​​is less than the predetermined threshold, the controller may determine that the predetermined fault has not occurred in the fuel cell system.

[0054] by Figure 4 For example, the controller can determine that the fuel cell system is in an abnormal state, such as when the number of integrated values ​​within the range of N1 to N2 exceeds a first threshold, e.g., when the nitrogen concentration exceeds a normal nitrogen concentration range or the water content exceeds a normal water content range. The controller can also determine that a predetermined fuel cell system fault has occurred when the number of integrated values ​​greater than N2 exceeds a second threshold. This allows the fault state to be determined based on multiple tests, avoiding detection errors due to accidental errors and ensuring more accurate test results.

[0055] In some embodiments, the controller can execute different handling strategies based on different fault conditions. In some embodiments, the predetermined fault is a flooding fault. If the water content in the anode circuit is determined to be within a normal range, the controller can control the drain valve to open at a predefined frequency to drain the water separated by the water separator. In some embodiments, the controller can determine that the water content in the anode circuit is too low based on the integrated value of the target signal and control the drain valve to remain closed.

[0056] In some embodiments, if the water content of the anode circuit is determined to be outside the normal water content range, the controller can adjust the opening frequency of the drain valve in the fuel cell system so that the opening frequency of the drain valve is greater than the opening frequency when the water content is within the normal water content range. In this way, excess water in the anode circuit can be drained in a timely manner to avoid anode flooding. In some embodiments, the controller can determine the opening frequency of the drain valve based on the integral value of the target signal. The corresponding relationship between the opening frequency of the drain valve and the integral value can be predefined. In this way, the drainage strategy of the fuel cell system can be adjusted in a timely manner based on the detection results, so that excess water is discharged appropriately, thereby avoiding fuel cell flooding.

[0057] In some embodiments, the predetermined fault is a high nitrogen concentration fault. Upon determining that the nitrogen concentration in the anode circuit is within a normal nitrogen concentration range, the controller may control the fuel cell system's hydrogen drain valve to open at a predefined frequency to properly drain nitrogen from the anode circuit, thereby maintaining the hydrogen concentration in the anode circuit within a normal range. In some embodiments, the controller may control the hydrogen drain valve to remain closed.

[0058] In some embodiments, when it is determined that the nitrogen concentration in the anode circuit exceeds the normal nitrogen concentration range, the controller can control the hydrogen drain valve to open at a higher frequency, which is greater than the opening frequency when it is within the normal concentration range. In this way, the excess nitrogen in the anode circuit can be discharged to avoid the hydrogen concentration in the anode being too low, thereby avoiding the situation of insufficient hydrogen. In some embodiments, the controller can determine the opening frequency of the hydrogen drain valve based on the integral value of the target signal. The correspondence between the opening frequency of the hydrogen drain valve and the integral value can be predefined. In this way, the hydrogen drain strategy of the fuel cell system can be adjusted in a timely manner based on the detection results, so that the excess nitrogen in the anode circuit is discharged appropriately without wasting hydrogen, thereby avoiding the hydrogen concentration in the anode circuit being too low, thereby avoiding the situation of insufficient hydrogen.

[0059] In some embodiments, if a predetermined fuel cell system fault is detected, such as a flooding fault or a high nitrogen concentration fault, the controller can issue an alarm signal to remind the user to promptly repair the fuel cell system. In some embodiments, if a predetermined fuel cell system fault is detected, the controller can shut down the fuel cell system to prevent damage to the fuel cell system's membrane electrode from continued operation under flooding or high nitrogen concentration conditions. This can improve the stability of the fuel cell system.

[0060] Figure 5 1 shows a schematic flow chart of a method 500 for detecting flooding of a fuel cell system according to some embodiments of the present disclosure. The method 500 may be executed by a controller, which may be, for example, Figure 1 FCCU 130 in. Reference Figure 5, method 500 may include boxes 501 to 509. In box 501, the controller obtains the current signal of the hydrogen circulation pump. In box 502, the controller generates a plurality of target signals corresponding to a plurality of time windows based on a predetermined reference signal and the current signal. The frequency of the predetermined reference signal corresponds to a flooding fault. In some embodiments, the predetermined reference signal may be a plurality of wavelet basis signals corresponding to a plurality of time windows, and the plurality of wavelet basis signals may be multiplied by the current signal obtained in box 501 to obtain a plurality of target signals. In some embodiments, the controller may multiply the predetermined reference signal by the signals in a plurality of time windows in the current signal to obtain a plurality of target signals.

[0061] In box 503, the controller integrates multiple signals in their respective corresponding time windows to obtain multiple integral values. In box 504, the controller determines the number of integral values ​​within the range of the first integral threshold and the second integral threshold (referred to as the first number). The controller determines the number of integral values ​​greater than the second integral threshold (referred to as the second number). In box 505, the control situation determines whether the second number is greater than the predefined second number threshold. If so, execute box 506; if not, execute box 507. In box 506, the controller determines that a water flooding fault has occurred in the fuel cell system and sends a corresponding fault indication message. In box 507, the controller determines whether the first number is greater than the predefined first number threshold. If so, execute box 508; if not, execute box 509. In box 508, the controller adjusts the opening frequency of the drain valve in the fuel cell system. In box 509, the controller determines that the water content in the anode circuit is within the normal water content range.

[0062] In method 500, the detection of the flooding state of the anode circuit of the fuel cell system is performed on the basis of multiple time windows, which can make the detection results more accurate. In addition, the different water content states of the anode circuit can be determined, and different treatment measures can be taken on this basis, which can make the detection and treatment of flooding more adaptable and flexible. Through method 500, treatment measures can be taken in a timely manner when the water content of the anode circuit increases, thereby avoiding the resulting hydrogen shortage and avoiding damage to the membrane electrode due to hydrogen shortage. In this way, the stability of the fuel cell system can be improved.

[0063] Figure 6 A schematic flow chart of a method 600 for detecting the nitrogen state of a fuel cell system according to some embodiments of the present disclosure is shown. The method 600 may be executed by a controller, which may be, for example, Figure 1 FCCU130 in. Reference Figure 6Method 600 may include blocks 601 to 609. In block 601, the controller obtains a current signal from the hydrogen circulation pump. In block 602, the controller generates multiple target signals corresponding to multiple time windows based on a predetermined reference signal and the current signal, wherein the frequency of the predetermined reference signal corresponds to a high nitrogen concentration fault. Block 602 may be executed with reference to block 601.

[0064] In block 603, the controller integrates the multiple signals within their respective time windows to obtain multiple integral values. In block 604, the controller determines the number of integral values ​​within a range between a third integral threshold and a fourth integral threshold (referred to as a third integral value). The controller determines the number of integral values ​​greater than the fourth integral threshold (referred to as a fourth integral value). In block 605, the controller determines whether the fourth integral value is greater than a predefined fourth integral value threshold. If so, the controller executes block 606; if not, the controller executes block 607. In block 606, the controller determines that the fuel cell system has a high nitrogen concentration fault and sends a corresponding fault indication message. In some embodiments, the controller may determine that the fuel cell system has a low hydrogen concentration fault. In block 607, the controller determines whether the third integral value is greater than a predefined third integral value threshold. If so, the controller executes block 608; if not, the controller executes block 609. In block 608, the controller adjusts the opening frequency of the hydrogen purge valve in the fuel cell system. In block 609, the controller determines that the nitrogen concentration in the anode circuit is within a normal nitrogen concentration range.

[0065] In method 600, the detection of the nitrogen state of the anode circuit of the fuel cell system is performed on the basis of multiple time windows, so that the detection results can be more accurate. In addition, the different nitrogen concentration states of the anode circuit can be determined, and different treatment measures can be taken on this basis, which can make the detection and treatment of the nitrogen state more adaptable and flexible. Through method 600, treatment measures can be taken in time when the nitrogen concentration in the anode circuit increases or the hydrogen concentration decreases, thereby avoiding the resulting hydrogen shortage and avoiding damage to the membrane electrode due to hydrogen shortage. In this way, the stability of the fuel cell system can be improved.

[0066] It should be understood that Figure 5 The method 500 and Figure 6 The illustrated method 600 is merely an example of an embodiment of the present disclosure and is not intended to limit the solutions provided herein. For example, in some embodiments, method 500 may include more integration thresholds to determine a wider range of water content states. For another example, in some embodiments, method 600 may include more integration thresholds to determine a wider range of nitrogen concentration states. It should also be understood that methods 500 and 600 may be implemented in combination. For example, in some embodiments, a flooding state and a nitrogen concentration state may be simultaneously determined based on a single current signal.

[0067] Figure 7 FIG. 7 is a block diagram of an apparatus 700 for detecting a fault in a fuel cell system according to some embodiments of the present disclosure. Figure 7 As shown, apparatus 700 includes an acquisition unit 702 configured to acquire a current signal of a hydrogen circulation pump in a fuel cell system. Apparatus 700 also includes a signal conversion unit 704 configured to generate a target signal based on the current signal and a predetermined reference signal, wherein the frequency of the predetermined reference signal corresponds to a predetermined fault of the fuel cell system. Furthermore, apparatus 700 also includes a fault determination unit 706 configured to determine a fault state of the fuel cell system based on the target signal.

[0068] In some embodiments, the target signal is the product of the current signal and a predetermined reference signal, and the fault determination unit 706 includes a first fault determination unit configured to determine the fault state of the fuel cell system based on an integral value of the target signal within a predetermined time window.

[0069] In some embodiments, the predetermined reference signal is a wavelet basis signal, and the signal conversion unit 704 includes a first signal conversion unit, which is configured to multiply multiple predetermined reference signals corresponding to multiple time windows with the current signal respectively to generate multiple target signals; the first fault determination unit includes: an integration unit, which is configured to integrate the multiple target signals in multiple predetermined time windows respectively to obtain multiple integral values; and a second fault determination unit, which is configured to determine the fault state of the fuel cell system based on the multiple integral values.

[0070] In some embodiments, the apparatus 700 further includes a shutdown control unit configured to control the fuel cell system to shut down in response to determining that a predetermined fault occurs in the fuel cell system.

[0071] In some embodiments, the predetermined fault is a water flooding fault, and the first fault determination unit includes a third fault determination unit, which is configured to determine that the water content in the anode circuit of the fuel cell system exceeds the normal water content range in response to the integral value being within the range of a first integral threshold and a second integral threshold, wherein the first integral threshold is less than the second integral threshold; or, the first fault determination unit includes a fourth fault determination unit, which is configured to determine that a water flooding fault occurs in the fuel cell system in response to the integral value being greater than the second integral threshold.

[0072] In some embodiments, the device 700 also includes a drain valve control unit, which is configured to control the drain valve of the fuel cell system to open at a first predetermined frequency in response to determining that the water content in the anode loop of the fuel cell system exceeds the normal water content range. The first predetermined frequency is greater than the opening frequency of the drain valve when the water content in the anode loop of the fuel cell system is within the normal water content range.

[0073] In some embodiments, the predetermined fault is a high nitrogen concentration fault, and the first fault determination unit includes a fifth fault determination unit, which is configured to determine that the nitrogen concentration in the anode circuit of the fuel cell system exceeds the normal nitrogen concentration range in response to the integral value being within the range of a third integral threshold and a fourth integral threshold, wherein the third integral threshold is less than the fourth integral threshold; or, the first fault determination unit includes a sixth fault determination unit, which is configured to determine that a high nitrogen concentration fault occurs in the fuel cell system in response to the integral value being greater than the fourth integral threshold.

[0074] In some embodiments, the device 700 also includes a hydrogen drain valve control unit, which is configured to control the hydrogen drain valve of the fuel cell system to open at a second predetermined frequency in response to determining that the nitrogen concentration in the anode loop of the fuel cell system exceeds a normal nitrogen concentration range. The second predetermined frequency is greater than the opening frequency of the hydrogen drain valve when the nitrogen concentration in the anode loop of the fuel cell system is within a normal nitrogen concentration range.

[0075] In some embodiments, the device 700 also includes: a fault signal acquisition unit, configured to acquire a fault current signal of the hydrogen circulation pump when a predetermined fault occurs in the fuel cell system; and a reference signal determination unit, configured to determine the predetermined reference signal based on the wavelet transform result of the fault current signal.

[0076] Figure 8 FIG1 shows a schematic block diagram of an example device 800 that can be used to implement an embodiment of the present disclosure. The device 800 may correspond to the controller in the aforementioned method embodiment. Figure 1 The FCCU 130 in FIG. 8 can also be implemented using the device 800. Figure 8 As shown, the device 800 includes a processor 801, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 802 and loaded into a random access memory (RAM) 803. Various programs and data required for the operation of the device 800 can also be stored in the RAM 803. The processor 801, ROM 802, and RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0077] The various processes and procedures described above, such as method 200, method 500, or method 600, may be executed by processor 801. For example, in some embodiments, method 200, method 500, or method 600 may be implemented as a software program tangibly embodied on a machine-readable medium. In some embodiments, part or all of the software program may be loaded and / or installed onto device 800 via ROM 802. When the software program is loaded into RAM 803 and executed by processor 801, one or more actions of method 200, method 500, or method 600 described above may be performed.

[0078] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), and the like.

[0079] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0080] The present disclosure may be a method, apparatus, system and / or program product. The program product may include a machine-readable storage medium on which are loaded machine-readable program instructions for executing various aspects of the present disclosure. The machine-readable program instructions described herein may be downloaded from the machine-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network and / or a wireless network. The network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. The network adapter card or network interface in each computing / processing device receives the machine-readable program instructions from the network and forwards the machine-readable program instructions for storage in the machine-readable storage medium in each computing / processing device.

[0081] The machine program instructions for performing the operation of the present disclosure can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, and conventional procedural programming languages ​​such as "C" language or similar programming languages. Machine-readable program instructions can be executed entirely on a user's computer, partially on a user's computer, executed as an independent software package, partially on a user's computer and partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., utilizing an Internet service provider to connect via the Internet). In some embodiments, by utilizing the state information of a machine-readable program instruction to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the machine-readable program instruction, thereby realizing various aspects of the present disclosure.

[0082] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or apparatus. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In addition, although each operation is depicted in a specific order, this should be understood as requiring that such operations be performed in the specific order shown or in a sequential order, or requiring that all illustrated operations be performed to obtain the desired result. In certain environments, multitasking and parallel processing may be advantageous. Likewise, although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of separate embodiments may also be implemented in combination in a single implementation. Conversely, various features described in the context of a single implementation may also be implemented in multiple implementations individually or in any suitable subcombination.

[0083] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A method (200) for detecting a fault in a fuel cell system, comprising: Acquiring (202) a current signal of a hydrogen circulation pump in the fuel cell system; generating (204) a target signal based on the current signal and a predetermined reference signal, wherein a frequency of the predetermined reference signal corresponds to a predetermined fault of the fuel cell system; as well as Based on the target signal, a fault state of the fuel cell system is determined (206).

2. The method of claim 1 , wherein the target signal is a product of the current signal and the predetermined reference signal, and wherein determining ( 206 ) a fault state of the fuel cell system based on the target signal comprises: The fault state is determined based on an integrated value of the target signal within a predetermined time window.

3. The method (200) of claim 2, wherein the predetermined reference signal is a wavelet basis signal, and wherein generating (204) a target signal based on the current signal and the predetermined reference signal comprises: multiplying the current signal by a plurality of predetermined reference signals corresponding to a plurality of time windows to generate a plurality of target signals; Wherein determining the fault state based on the integral value of the target signal within a predetermined time window comprises: Integrating the multiple target signals respectively within the multiple predetermined time windows to obtain multiple integral values; as well as The fault status is determined based on the plurality of integrated values.

4. The method (200) according to claim 2 or 3, further comprising: In response to determining that the predetermined fault occurs in the fuel cell system, the fuel cell system is controlled to shut down.

5. The method (200) according to claim 2, wherein the predetermined fault is a flooding fault, and wherein determining the fault state based on an integral value of the target signal within a predetermined time window comprises: determining that the water content in the anode circuit of the fuel cell system exceeds a normal water content range in response to the integrated value being within a range of a first integration threshold and a second integration threshold, wherein the first integration threshold is less than the second integration threshold; or In response to the integrated value being greater than the second integrated threshold, it is determined that the flooding fault occurs in the fuel cell system.

6. The method (200) of claim 5, further comprising: In response to determining that the water content in the anode loop of the fuel cell system exceeds a normal water content range, the drain valve of the fuel cell system is controlled to open at a first predetermined frequency, wherein the first predetermined frequency is greater than the opening frequency of the drain valve when the water content in the anode loop of the fuel cell system is within the normal water content range.

7. The method (200) of claim 2, wherein the predetermined fault is a high nitrogen concentration fault, and wherein determining the fault state based on an integral value of the target signal within a predetermined time window comprises: determining that a nitrogen concentration in an anode circuit of the fuel cell system exceeds a normal nitrogen concentration range in response to the integrated value being within a range of a third integrated threshold and a fourth integrated threshold, wherein the third integrated threshold is less than the fourth integrated threshold; or In response to the integrated value being greater than the fourth integrated threshold, it is determined that the high nitrogen concentration fault occurs in the fuel cell system.

8. The method (200) of claim 7, further comprising: In response to determining that the nitrogen concentration in the anode loop of the fuel cell system exceeds a normal nitrogen concentration range, the hydrogen drain valve of the fuel cell system is controlled to open at a second predetermined frequency, wherein the second predetermined frequency is greater than the opening frequency of the hydrogen drain valve when the nitrogen concentration in the anode loop of the fuel cell system is within the normal nitrogen concentration range.

9. The method (200) of claim 1, further comprising: acquiring a fault current signal of the hydrogen circulation pump when the predetermined fault occurs in the fuel cell system; as well as The predetermined reference signal is determined based on a wavelet transform result of the fault current signal.

10. A device (700) for detecting a fault in a fuel cell system, comprising: An acquisition unit (702) is configured to acquire a current signal of a hydrogen circulation pump in the fuel cell system; a signal conversion unit (704) configured to generate a target signal based on the current signal and a predetermined reference signal, wherein a frequency of the predetermined reference signal corresponds to a predetermined fault of the fuel cell system; as well as A fault determination unit (706) is configured to determine a fault state of the fuel cell system based on the target signal.

11. A controller comprising: at least one processor; as well as A memory coupled to the at least one processor and having instructions stored thereon, the instructions causing the controller to perform the method according to any one of claims 1 to 9 when executed by the at least one processor.

12. A fuel cell system comprising the controller according to claim 11.

13. A program product tangibly stored on a non-transitory machine-readable medium and comprising machine-executable instructions which, when executed, cause a machine to perform the steps of the method according to any one of claims 1 to 9.

Images