Pressure sensor fault data analysis method, device and electronic equipment

Abstract

The application provides a pressure sensor fault data analysis method, device and electronic equipment, and belongs to the technical field of fuel cells.The pressure sensor fault data analysis method of the application determines a target pressure sensor that may have a fault by acquiring fault logs and analyzing fault data of various types of pressure sensors, further analyzes pressure detection data values of other pressure sensors before and after a fault period of the target pressure sensor according to an association relationship between detection data of various types of pressure sensors, can accurately identify a cause of abnormal detection data of the target pressure sensor, and can further identify a fault risk of a related device in an anode hydrogen gas pipeline, thereby providing an accurate basis for maintenance of a fuel cell vehicle.

Description

Technical Field

[0001] This invention relates to the field of fuel cell technology, and in particular to a method, apparatus, and electronic device for analyzing fault data of a pressure sensor. Background Technology

[0002] Hydrogen-oxygen fuel cell vehicles use a proton exchange membrane fuel cell system as their core, which uses high-purity hydrogen to react with oxygen in the air to generate electricity to power the vehicle. Hydrogen-oxygen fuel cells are a zero-emission or near-zero-emission on-board power solution, with advantages such as smooth operation, low noise, high economy, fast refueling, and strong environmental adaptability.

[0003] Fuel cell vehicles use hydrogen as fuel, but hydrogen is highly flammable and explosive, making its safe use in fuel cell systems crucial. Pressure sensors are typically installed at the anode inlet and outlet of the fuel cell stack to monitor the hydrogen supply and provide information for diagnosing safety risks such as hydrogen leaks. However, the internal environment of a fuel cell system is extremely complex, with fluctuating temperature, humidity, and pressure. Due to the randomness of pressure sensor measurements, errors can occur. Furthermore, internal malfunctions within the fuel cell can also cause anomalies in the sensor data. In the event of a faulty pressure sensor, its data will also be abnormal.

[0004] When pressure sensor data becomes abnormal, a fault log is generated. In cases of internal fuel cell faults, if the fault is severe and prolonged, the fault log will show widespread, consecutive faults across multiple pressure sensors. However, when the fault is minor and short-lived, the complex internal environment of the fuel cell and the lag in pressure changes at different locations mean that fluctuations in pressure sensor data may be perceived as within the normal range, failing to promptly diagnose the fault and thus not generating a fault log. If a pressure sensor's data exceeds the normal range, the system will only issue a simple error message, warning of potential faults such as damage, unreliable installation, or poor wiring connections. This ignores the impact of minor faults on pressure sensor data, failing to accurately identify faults in the hydrogen path within the fuel cell and the operating status of the pressure sensors, thus failing to pinpoint the cause of the abnormal pressure sensor data at the anode. Summary of the Invention

[0005] This invention provides a method, apparatus, and electronic device for analyzing fault data of a pressure sensor, which solves the defect in the prior art that cannot accurately identify the cause of abnormal data of the pressure sensor at the anode, and achieves the effect of accurately identifying the cause of abnormal detection data of the target pressure sensor.

[0006] This invention provides a method for analyzing pressure sensor fault data, comprising: Obtain the fault log of the pressure sensor of the stack anode during the target time period. The pressure sensor types include at least the ejector inlet pressure sensor, the anode inlet pressure sensor, and the anode outlet pressure sensor. Based on the fault logs of various types of pressure sensors, the fault frequency of each type of pressure sensor within the target time period is determined. The target pressure sensor is determined based on the failure frequency of each type of pressure sensor. Acquire target detection data of pressure sensors of other types besides the target pressure sensor among various types of pressure sensors in the first time period and the second time period; the first time period is the period before the start time of the current fault period of the target pressure sensor, and the second time period is the period after the end time of the current fault period of the target pressure sensor; Based on the correlation between the target detection data and the detection data of various types of pressure sensors, the working state of the target pressure sensor is determined; the working state of the target pressure sensor includes normal state and fault state.

[0007] According to a pressure sensor fault data analysis method provided by the present invention, when the target pressure sensor includes the ejector inlet pressure sensor, the operating state of the target pressure sensor is determined based on the correlation between the target detection data and the detection data of various types of pressure sensors, including: Based on the target detection data, the first change and the second change of the pressure detection values ​​of the anode inlet pressure sensor and the anode outlet pressure sensor in the second time period relative to the first time period are determined respectively. The operating state of the ejector inlet pressure sensor is determined based on the magnitudes of the first and second changes.

[0008] According to a pressure sensor fault data analysis method provided by the present invention, when the target pressure sensor includes the anode inlet pressure sensor, the operating state of the target pressure sensor is determined based on the correlation between the target detection data and the detection data of various types of pressure sensors, including: Based on the target detection data, a first trend of change of the pressure detection value of the ejector inlet pressure sensor during the first time period and a third change of the pressure detection value of the anode outlet pressure sensor in the second time period relative to the pressure detection value of the first time period are determined. Based on the first trend and the third change, the operating state of the anode inlet pressure sensor is determined.

[0009] According to a pressure sensor fault data analysis method provided by the present invention, when the target pressure sensor includes the anode outlet pressure sensor, the operating state of the target pressure sensor is determined based on the correlation between the target detection data and the detection data of various types of pressure sensors, including: Based on the target detection data, the second and third trends of the pressure detection values ​​of the ejector inlet pressure sensor and the anode inlet pressure sensor are determined in the first time period, and the fourth change of the pressure detection value of the anode inlet pressure sensor in the second time period relative to the pressure detection value in the first time period is determined. Based on the second trend, the third trend, and the fourth change, the operating state of the anode outlet pressure sensor is determined.

[0010] According to a pressure sensor fault data analysis method provided by the present invention, the step of acquiring target detection data of other types of pressure sensors besides the target pressure sensor in a first time period and a second time period includes: Acquire all detection data from pressure sensors of all types other than the target pressure sensor during the first and second time periods; Based on the fault logs of the pressure sensor of the stack anode during the target time period, fault detection data of other types of pressure sensors besides the target pressure sensor are determined in the first and second time periods. The target detection data is obtained by removing fault detection data from all detection data of pressure sensors of all types except the target pressure sensor in the first and second time periods.

[0011] According to a pressure sensor fault data analysis method provided by the present invention, the step of determining the target pressure sensor based on the fault frequency of various types of pressure sensors includes: Determine the fault standard duration for each type of pressure sensor; if the detection data of the pressure sensor deviates from the target range of the fault standard duration, the fault log of the pressure sensor is updated. Based on the type of each pressure sensor, the fault standard duration corresponding to the pressure sensor, and the duration of the target time period, the frequency threshold corresponding to each pressure sensor is determined. If the failure frequency of a pressure sensor exceeds a corresponding frequency threshold, the pressure sensor is identified as the target pressure sensor.

[0012] According to a pressure sensor fault data analysis method provided by the present invention, the fault log is determined in the following manner: Obtain the current target operating condition parameters of the fuel cell stack; the target operating condition parameters are output current or output power. Based on the target operating condition parameters, determine the target range of pressure detection values ​​for each pressure sensor; If the duration during which the pressure sensor's pressure detection value deviates from the target range is greater than or equal to the fault standard duration corresponding to the pressure sensor, the fault period during which the pressure sensor's pressure detection value continuously deviates from the target range is recorded to obtain the fault log.

[0013] The present invention also provides a pressure sensor fault data analysis device, comprising: The acquisition module is used to acquire the fault log of the pressure sensor of the stack anode within the target time period. The pressure sensor includes at least the ejector inlet pressure sensor, the anode inlet pressure sensor, and the anode outlet pressure sensor. The first processing module is used to determine the failure frequency of each type of pressure sensor within the target time period based on the failure logs of each type of pressure sensor. The determination module is used to determine the target pressure sensor based on the failure frequency of each type of pressure sensor; The second processing module is used to acquire target detection data of other types of pressure sensors besides the target pressure sensor among various types of pressure sensors in the first time period and the second time period; the first time period is the period before the start time of the current fault period of the target pressure sensor, and the second time period is the period after the end time of the current fault period of the target pressure sensor. The third processing module is used to determine the working state of the target pressure sensor based on the correlation between the target detection data and the detection data of various types of pressure sensors; the working state of the target pressure sensor includes normal state and fault state.

[0014] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the pressure sensor fault data analysis method as described above.

[0015] The present invention also provides a fuel cell, including a stack and electronic equipment as described above.

[0016] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the pressure sensor fault data analysis method as described above.

[0017] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the pressure sensor fault data analysis method as described above.

[0018] The pressure sensor fault data analysis method, device, and electronic equipment provided by this invention acquire fault logs and analyze fault data of various types of pressure sensors to identify potential faulty target pressure sensors. Furthermore, based on the correlation between the detection data of various types of pressure sensors, the pressure detection data values ​​of other pressure sensors before and after the fault period of the target pressure sensor are analyzed. This can accurately identify the cause of the abnormal detection data of the target pressure sensor, and further identify the fault risks of related components in the anode hydrogen pipeline, providing an accurate basis for the maintenance of fuel cell vehicles. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0020] Figure 1 This is one of the flowcharts illustrating the pressure sensor fault data analysis method provided by the present invention; Figure 2 This is the second flowchart of the pressure sensor fault data analysis method provided by the present invention; Figure 3 This is a schematic diagram of the pressure sensor fault data analysis device provided by the present invention; Figure 4 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0022] The following is combined Figures 1-4 The present invention describes a method, apparatus, and electronic device for analyzing fault data of a pressure sensor.

[0023] like Figure 1As shown, the pressure sensor fault data analysis method of this invention mainly includes steps 110, 120, 130, 140 and 150.

[0024] Step 110: Obtain the fault log of the pressure sensor of the fuel cell anode during the target time period.

[0025] Pressure sensors are typically installed at the anode of the fuel cell stack. These sensors monitor the pressure of the hydrogen gas within the fuel cell stack.

[0026] The pressure sensor measures the hydrogen pressure at the anode location in real time and transmits the data to the vehicle's control system. The vehicle's control system can then take appropriate measures based on changes in hydrogen pressure, such as adjusting the hydrogen supply and flow rate, to ensure the normal operation and safety of the fuel cell stack.

[0027] By monitoring the hydrogen pressure through pressure sensors, the control system can record any abnormalities and generate a fault log. In more serious cases, the control system can also issue alarms or take automatic shutdown measures to avoid potential safety risks.

[0028] In this embodiment, the pressure sensor types include at least an ejector inlet pressure sensor, an anode inlet pressure sensor, and an anode outlet pressure sensor.

[0029] The anode ejector draws hydrogen from the fuel cell stack outlet and recirculates it, then recombines it with the hydrogen supplied by the hydrogen supply system before resupplying the stack. This ensures sufficient flow, achieving high anode hydrogen pressure and preventing flooding. An ejector inlet pressure sensor detects the hydrogen pressure supplied by the hydrogen supply system, an anode inlet pressure sensor detects the hydrogen pressure supplied by the ejector to the anode, and an anode outlet pressure sensor detects the gas pressure discharged from the anode. When the anode hydrogen circulation path is stable, the ejector recirculation inlet pressure is directly correlated with the anode outlet pressure sensor reading.

[0030] The target time period is the period during which the fuel cell vehicle operates. The duration of the target time period can be set as needed, for example, it can be 10 minutes or 20 minutes, etc. There is no restriction here.

[0031] In some embodiments, the fault log can be determined in the following ways.

[0032] First, the target operating condition parameters of the fuel cell stack can be obtained, which are either output current or output power. Understandably, the range of gas pressure at different locations on the anode of the fuel cell under the target operating conditions can be calibrated in the laboratory. Based on these target operating conditions, the target range of pressure readings from each pressure sensor can then be determined.

[0033] It should be noted that, due to the complex internal environment of a fuel cell, the target range of pressure detection values ​​from different pressure sensors at different locations is quite long.

[0034] During the actual operation of fuel cells, the control system of fuel cell vehicles can collect, save and analyze the detection data of each pressure sensor. When the duration of the pressure detection value of the pressure sensor deviating from the target range is greater than or equal to the fault standard duration corresponding to the pressure sensor, the fault period when the pressure detection value of the pressure sensor continuously deviates from the target range is recorded to obtain a fault log.

[0035] Understandably, the fault log contains information about the types of pressure sensors whose detection data is abnormal, as well as the duration of the fault.

[0036] The fault standard duration can be set according to the data acquisition frequency corresponding to different types of pressure sensors and the fault data of historical fault cases.

[0037] Step 120: Based on the fault logs of each type of pressure sensor, determine the fault frequency of each type of pressure sensor within the target time period.

[0038] Understandably, the failure frequency of each type of pressure sensor within the target time period can be determined based on the fault logs of each type of pressure sensor, that is, the number of times each type of pressure sensor has abnormal data within the target time period can be counted.

[0039] Step 130: Determine the target pressure sensor based on the failure frequency of each type of pressure sensor.

[0040] It is understandable that when the failure frequency is too low, abnormal pressure sensor detection data may be caused by random errors in the detection process. The target pressure sensor is a pressure sensor that may be faulty. In this embodiment, based on the failure frequency of each type of pressure sensor, the target pressure sensor that may be in a faulty state can be screened out, eliminating the influence of random errors in the detection process.

[0041] In some embodiments, pressure sensors with a failure frequency greater than the corresponding frequency threshold can be directly used as target pressure sensors.

[0042] In this case, determining the target pressure sensor based on the failure frequency of each type of pressure sensor may include steps 131, 132, and 133.

[0043] Step 131: Determine the standard fault duration for each type of pressure sensor.

[0044] The standard fault duration for each type of pressure sensor can be determined first. When the pressure sensor's detection data deviates from the target range of the standard fault duration, the fault period of the pressure sensor is recorded, and the fault log is updated.

[0045] Step 132: Determine the frequency threshold for each pressure sensor based on the type of each pressure sensor, the fault standard duration corresponding to the pressure sensor, and the duration of the target time period.

[0046] Different types of pressure sensors have different target ranges for detecting pressure values, and the fluctuation patterns of the detected pressure value data also differ within different target ranges. When the target range for detected pressure values ​​is smaller, the fluctuation of the detected pressure value data is smaller, and the ratio of the fault standard duration to the target time period is larger, the corresponding frequency threshold for the pressure sensor will be smaller.

[0047] Step 133: If the failure frequency of the pressure sensor is greater than the corresponding frequency threshold, the pressure sensor is identified as the target pressure sensor.

[0048] If the failure frequency of a pressure sensor exceeds the corresponding frequency threshold, the pressure sensor may be in a faulty state, and thus the pressure sensor can be identified as the target pressure sensor.

[0049] In this embodiment, by setting frequency thresholds for different pressure sensors based on the type of pressure sensor, the fault standard duration corresponding to the pressure sensor, and the duration of the target time period, the influence of random errors on the detected pressure value of the pressure sensor during the target time period can be more accurately eliminated. This allows for the selection of more valuable fault log data, providing a more accurate basis for fault identification.

[0050] Of course, in other embodiments, historical data of vehicles previously equipped with the same fuel cell and sensors can be directly analyzed to obtain the frequency of abnormalities in the fault log due to accidental errors of the pressure sensor. This data can then be compared with the fault frequencies of various types of pressure sensors to determine the target pressure sensor.

[0051] Step 140: Obtain target detection data from pressure sensors of other types besides the target pressure sensor in the first and second time periods.

[0052] It is understandable that the first time period is the period before the start of the current fault period of the target pressure sensor, and the second time period is the period after the end of the current fault period of the target pressure sensor.

[0053] It should be noted that the duration of the first and second time periods depends on the hydrogen transport efficiency in the fuel cell. The duration of the first and second time periods reflects the gas conduction and equilibrium processes at different locations within the fuel cell system.

[0054] The duration of the first and second time periods can be set according to the type of fuel cell and its operating parameters.

[0055] Different fuel cell systems employ different hardware configurations and operate under different parameters, resulting in varying hydrogen transmission speeds and flow rates within the fuel cell. This, in turn, affects the rate of change in hydrogen pressure at the ejector inlet, anode inlet, and anode outlet.

[0056] It is understandable that the detection pressure values ​​of each pressure sensor stored in the control system of the fuel cell vehicle can be directly obtained, thereby obtaining the first detection data of the target pressure sensor in the target time period, as well as the target detection data of other types of pressure sensors besides the target pressure sensor in the first and second time periods.

[0057] For example, when the target pressure sensor is the ejector inlet pressure sensor, it is necessary to obtain the first detection data of the ejector inlet pressure sensor during the target time period, as well as the target detection data of the anode inlet pressure sensor and the anode outlet pressure sensor during the first and second time periods.

[0058] Step 150: Determine the working status of the target pressure sensor based on the correlation between the target detection data and the detection data of various types of pressure sensors.

[0059] It is understandable that the operating status of the target pressure sensor includes normal and fault states. After determining the operating status of the target pressure sensor, if the target pressure sensor is in a normal state, there is a risk of failure in the relevant components in the anode hydrogen pipeline. If the target pressure sensor is in a fault state, the installation method and wiring of the target pressure sensor need to be checked.

[0060] It should be noted that the correlation between the data detected by different types of pressure sensors is related to the internal structure of the fuel cell and the gas conduction and balance process at different locations where different pressure sensors are installed.

[0061] The correlation between the detection data of each type of pressure sensor can be determined based on the installation location of each type of pressure sensor and the transmission path of the anode hydrogen. Then, the pressure detection data of each type of pressure sensor at different locations can be analyzed with reference to the time of the fault data recorded in the fault log.

[0062] When the pressure reading of a target pressure sensor at one location is abnormal, if that sensor is faulty, the readings of pressure sensors at other locations will not be abnormal, and there will be no significant changes before and after the period when the faulty sensor is faulty. Conversely, if the target pressure sensor at one location is functioning normally, the readings of pressure sensors at other locations may not generate abnormal errors due to data fluctuations, but they will show observable changes before and after the period when the target pressure sensor's reading is abnormal, thus allowing for the determination of the target pressure sensor's operational status.

[0063] Only after determining the working status of the target pressure sensor can the cause of the target sensor data anomaly be identified more accurately, thereby providing a more accurate basis for the subsequent maintenance of fuel cell vehicles.

[0064] Understandably, when there are multiple abnormal data from multiple target pressure sensors, the abnormal data recorded in each fault log of each target pressure sensor can be analyzed separately to obtain multiple analysis results, which can then be used by relevant operation and maintenance personnel for comprehensive analysis and reference.

[0065] According to the pressure sensor fault data analysis method provided in the embodiments of the present invention, by acquiring fault logs and analyzing fault data of various types of pressure sensors, the target pressure sensor that may be faulty is identified. Furthermore, based on the correlation between the detection data of various types of pressure sensors, the pressure detection data values ​​of other pressure sensors before and after the fault period of the target pressure sensor are analyzed. The cause of the abnormal detection data of the target pressure sensor can be accurately identified. In addition, the fault risk of related devices in the anode hydrogen pipeline can also be identified, providing an accurate basis for the maintenance of fuel cell vehicles.

[0066] In some embodiments, when the target pressure sensor includes an ejector inlet pressure sensor, the operating state of the target pressure sensor is determined based on the target detection data and the correlation between the detection data of various types of pressure sensors, including the following process.

[0067] Based on the target detection data, the first and second changes in the pressure detection values ​​of the anode inlet pressure sensor and the anode outlet pressure sensor in the second time period relative to the first time period can be determined respectively.

[0068] It is understandable that if the hydrogen pipeline before the ejector inlet fails after the ejector inlet pressure becomes abnormal, the anode inlet and anode outlet will change after the hydrogen pressure at the ejector inlet becomes abnormal, depending on the hydrogen propagation path. Therefore, it is necessary to compare and analyze the detection pressure data of the anode inlet and anode outlet after the ejector inlet pressure becomes abnormal with the detection pressure data before the ejector inlet pressure becomes abnormal.

[0069] Therefore, based on the target detection data, all detection pressure values ​​of the anode inlet pressure sensor in the first and second time periods can be obtained, and the average value of all detection pressure values ​​of the anode inlet pressure sensor in the first time period can be calculated respectively. The difference between the average value in the second time period and the average value in the first time period can be obtained to obtain the first change.

[0070] Similarly, based on the target detection data, all detection pressure values ​​of the anode outlet pressure sensor in the first and second time periods can be obtained, and the average value of all detection pressure values ​​of the anode outlet pressure sensor in the first time period can be calculated. The difference between the average value in the second time period and the average value in the first time period can be obtained to obtain the second change.

[0071] In this case, the operating state of the ejector inlet pressure sensor can be determined based on the magnitude of the first and second changes.

[0072] If the first and second changes are small, it can be assumed that the pressure changes at the anode inlet and anode outlet are not significant. Therefore, it can be determined that the hydrogen pipeline before the ejector inlet is not faulty. In this case, the ejector inlet pressure sensor may be faulty, and thus the working state of the ejector inlet pressure sensor is determined to be faulty.

[0073] If the first and second changes are large, it can be considered that the pressure changes at the anode inlet and anode outlet are large, which can then be used to determine that the hydrogen pipeline before the ejector inlet may have malfunctioned, while the ejector inlet pressure sensor is in normal working condition.

[0074] In some embodiments, when the target pressure sensor includes an anode inlet pressure sensor, the operating state of the target pressure sensor is determined based on the target detection data and the correlation between the detection data of various types of pressure sensors, including the following process.

[0075] Based on the target detection data, the first trend of the pressure detection value of the ejector inlet pressure sensor during the first time period and the third change of the pressure detection value of the anode outlet pressure sensor during the second time period relative to the pressure detection value of the first time period are determined.

[0076] For example, the pressure detection value of the ejector inlet pressure sensor during the first time period can be fitted into a pressure value curve to obtain the slope of the continuous upward or downward trend of the pressure detection value of the ejector inlet pressure sensor during the last segment of the first time period, and thus obtain the first trend of increase or decrease.

[0077] Similarly, based on the target detection data, all detection pressure values ​​of the anode outlet pressure sensor in the first and second time periods can be obtained, and the average value of all detection pressure values ​​of the anode outlet pressure sensor in the first time period can be calculated. The difference between the average value in the second time period and the average value in the first time period can be used to obtain the third change.

[0078] Understandably, if a fault occurs in the hydrogen pipeline before the anode inlet after an abnormal anode inlet pressure, the hydrogen pressure at the ejector inlet will become abnormal before the anode inlet hydrogen pressure becomes abnormal, and the hydrogen pressure at the anode outlet will become abnormal after the anode inlet hydrogen pressure becomes abnormal. Therefore, it is necessary to analyze the hydrogen pressure at the ejector inlet before the anode inlet hydrogen pressure becomes abnormal and the hydrogen pressure at the anode outlet after the anode inlet hydrogen pressure becomes abnormal.

[0079] In this case, the operating status of the anode inlet pressure sensor can be determined based on the first trend and the third change.

[0080] If the first trend is not obvious and the third change is small, it can be assumed that the pressure changes at the ejector inlet and anode outlet are not significant. Therefore, it can be determined that the hydrogen pipelines before and after the anode inlet are not faulty, and the anode inlet pressure sensor may be faulty. Thus, the anode inlet pressure sensor is considered to be in a faulty state. Otherwise, the anode inlet pressure sensor is considered to be in a normal state.

[0081] It should be noted that the degree of the first trend can be measured by the slope of the last segment of the pressure value curve during the first period, where there is a sustained upward or downward trend. The steeper the slope, the more pronounced the trend.

[0082] If the first trend is relatively obvious, it can be determined that there may be an anomaly in the hydrogen pipeline before the ejector inlet; if the third change is large, it can be determined that there may be an anomaly in the ejector or the hydrogen pipeline before the ejector.

[0083] In some embodiments, when the target pressure sensor includes an anode outlet pressure sensor, the operating state of the target pressure sensor is determined based on the target detection data and the correlation between the detection data of various types of pressure sensors, including the following process.

[0084] Based on the target detection data, the second and third trends of the pressure detection values ​​of the ejector inlet pressure sensor and the anode inlet pressure sensor can be determined in the first time period, and the fourth change of the pressure detection value of the anode inlet pressure sensor in the second time period relative to the pressure detection value in the first time period can be determined.

[0085] It is understandable that the second and third trends can be determined in a similar manner to the first trend. For example, the pressure detection values ​​of the ejector inlet pressure sensor and the anode inlet pressure sensor during the first time period can be fitted into pressure value curves, thereby obtaining the slope of the continuous upward or downward trend of the pressure detection values ​​of the ejector inlet pressure sensor and the anode inlet pressure sensor during the last segment of the first time period, and thus obtaining the second and third trends of the rise or fall of the ejector inlet pressure sensor and the anode inlet pressure sensor, respectively.

[0086] Similarly, based on the target detection data, all detection pressure values ​​of the anode inlet pressure sensor in the first and second time periods can be obtained, and the average value of all detection pressure values ​​of the anode inlet pressure sensor in the first time period can be calculated. The difference between the average value in the second time period and the average value in the first time period can be used to obtain the fourth change.

[0087] Based on this, the operating status of the anode outlet pressure sensor can be determined by the second, third, and fourth changing trends.

[0088] If the second and third trends are not obvious, and the fourth change is small, it can be assumed that the pressure changes at the ejector inlet and anode inlet are not significant. Therefore, it can be determined that the hydrogen pipelines before and after the anode outlet are not faulty. In this case, the anode outlet pressure sensor may be faulty, thus determining that the anode outlet pressure sensor is in a faulty state. Otherwise, the anode inlet pressure sensor is in a normal state.

[0089] If the second trend is more obvious, it can be determined that there may be an anomaly in the hydrogen pipeline before the ejector inlet; if the third trend is more obvious, it can be determined that there may be an anomaly in the hydrogen pipeline before the ejector inlet or in the ejector itself; if the fourth trend is large, it can be determined that there may be an anomaly in the hydrogen pipeline at the anode outlet.

[0090] In some embodiments, acquiring target detection data from pressure sensors of other types besides the target pressure sensor in the first and second time periods may further include the following process.

[0091] We can first acquire all the detection data of all types of pressure sensors other than the target pressure sensor in the first and second time periods.

[0092] Based on this, and using the fault logs of the pressure sensor at the anode of the fuel cell stack during the target time period, fault detection data of other types of pressure sensors besides the target pressure sensor are determined in the first and second time periods.

[0093] Based on this, fault detection data can be removed from all detection data of pressure sensors of all types except the target pressure sensor in the first and second time periods to obtain the target detection data.

[0094] In this embodiment, by excluding fault detection data from all detection data of pressure sensors of all types other than the target pressure sensor in the first and second time periods, the accuracy of the analysis of the detected pressure values ​​in the first and second time periods can be improved, and the influence of possible faults of other pressure sensors can be eliminated.

[0095] The pressure sensor fault data analysis device provided by the present invention is described below. The pressure sensor fault data analysis device described below and the pressure sensor fault data analysis method described above can be referred to in correspondence.

[0096] like Figure 3 As shown, the pressure sensor fault data analysis device includes an acquisition module 310, a first processing module 320, a determination module 330, a second processing module 340, and a third processing module 350.

[0097] The acquisition module 310 is used to acquire the fault log of the pressure sensor of the stack anode during the target time period. The types of pressure sensors include at least the ejector inlet pressure sensor, the anode inlet pressure sensor, and the anode outlet pressure sensor. The first processing module 320 is used to determine the failure frequency of each type of pressure sensor within a target time period based on the fault logs of each type of pressure sensor. The determination module 330 is used to determine the target pressure sensor based on the failure frequency of each type of pressure sensor; The second processing module 340 is used to acquire target detection data of other types of pressure sensors besides the target pressure sensor among various types of pressure sensors in the first time period and the second time period; the first time period is the period before the start time of the current fault period of the target pressure sensor, and the second time period is the period after the end time of the current fault period of the target pressure sensor; The third processing module 350 is used to determine the working status of the target pressure sensor based on the correlation between the target detection data and the detection data of various types of pressure sensors; the working status of the target pressure sensor includes normal status and fault status.

[0098] The pressure sensor fault data analysis device provided in this embodiment of the invention acquires fault logs and analyzes fault data of various types of pressure sensors to identify potential faulty target pressure sensors. Furthermore, based on the correlation between the detection data of various types of pressure sensors, it analyzes the pressure detection data values ​​of other pressure sensors before and after the fault period of the target pressure sensor. This can accurately identify the cause of the abnormal detection data of the target pressure sensor, and further identify the fault risks of related devices in the anode hydrogen pipeline, providing an accurate basis for the maintenance of fuel cell vehicles.

[0099] Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown, the electronic device may include: a processor 410, a communications interface 420, a memory 430, and a communications bus 440, wherein the processor 410, the communications interface 420, and the memory 430 communicate with each other through the communications bus 440. The processor 410 can call logic instructions in the memory 430 to execute a pressure sensor fault data analysis method. This method includes: acquiring fault logs of the pressure sensors at the anode of the fuel cell stack during a target time period; the types of pressure sensors include at least an ejector inlet pressure sensor, an anode inlet pressure sensor, and an anode outlet pressure sensor; determining the fault frequency of each type of pressure sensor during the target time period based on the fault logs of each type of pressure sensor; determining the target pressure sensor based on the fault frequency of each type of pressure sensor; acquiring target detection data of other types of pressure sensors besides the target pressure sensor during a first time period and a second time period; the first time period is the period before the start time of the current fault period of the target pressure sensor, and the second time period is the period after the end time of the current fault period of the target pressure sensor; determining the operating state of the target pressure sensor based on the target detection data and the correlation between the detection data of each type of pressure sensor; the operating state of the target pressure sensor includes a normal state and a fault state.

[0100] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0101] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the pressure sensor fault data analysis method provided by the above methods. The method includes: acquiring fault logs of the pressure sensors of the stack anode during a target time period, wherein the types of pressure sensors include at least an ejector inlet pressure sensor, an anode inlet pressure sensor, and an anode outlet pressure sensor; determining the fault frequency of each type of pressure sensor during the target time period based on the fault logs of each type of pressure sensor; determining the target pressure sensor based on the fault frequency of each type of pressure sensor; acquiring target detection data of other types of pressure sensors besides the target pressure sensor during a first time period and a second time period; wherein the first time period is the period before the start time of the current fault period of the target pressure sensor, and the second time period is the period after the end time of the current fault period of the target pressure sensor; and determining the working state of the target pressure sensor based on the target detection data and the correlation between the detection data of each type of pressure sensor; wherein the working state of the target pressure sensor includes a normal state and a fault state.

[0102] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the pressure sensor fault data analysis method provided by the above methods. This method includes: acquiring fault logs of pressure sensors at the anode of the fuel cell stack during a target time period, wherein the types of pressure sensors include at least an ejector inlet pressure sensor, an anode inlet pressure sensor, and an anode outlet pressure sensor; determining the fault frequency of each type of pressure sensor during the target time period based on the fault logs of each type of pressure sensor; determining a target pressure sensor based on the fault frequency of each type of pressure sensor; acquiring target detection data of other types of pressure sensors besides the target pressure sensor during a first time period and a second time period; wherein the first time period is the period before the start time of the current fault period of the target pressure sensor, and the second time period is the period after the end time of the current fault period of the target pressure sensor; and determining the operating state of the target pressure sensor based on the target detection data and the correlation between the detection data of each type of pressure sensor; wherein the operating state of the target pressure sensor includes a normal state and a fault state.

[0103] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0104] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for analyzing fault data of a pressure sensor, characterized in that, include: Obtain the fault log of the pressure sensor of the stack anode during the target time period. The pressure sensor types include at least the ejector inlet pressure sensor, the anode inlet pressure sensor, and the anode outlet pressure sensor. Based on the fault logs of various types of pressure sensors, the fault frequency of each type of pressure sensor within the target time period is determined. Based on the failure frequency of each type of pressure sensor, the standard failure duration of each type of pressure sensor is determined. If the detection data of the pressure sensor deviates from the target range of the fault standard duration, the fault log of the pressure sensor is updated; based on the type of each pressure sensor, the fault standard duration corresponding to the pressure sensor, and the duration of the target time period, a frequency threshold corresponding to each pressure sensor is determined; if the fault frequency of the pressure sensor is greater than the corresponding frequency threshold, the pressure sensor is identified as the target pressure sensor. Acquire target detection data of pressure sensors of other types besides the target pressure sensor in each type of pressure sensor during the first time period and the second time period; acquire all detection data of pressure sensors of other types besides the target pressure sensor in each type of pressure sensor during the first time period and the second time period; based on the fault log of the pressure sensor of the stack anode during the target time period, determine the fault detection data of pressure sensors of other types besides the target pressure sensor in each type of pressure sensor during the first time period and the second time period; remove the fault detection data from all detection data of pressure sensors of other types besides the target pressure sensor in each type of pressure sensor during the first time period and the second time period to obtain the target detection data; The first time period is the period before the start time of the current fault period of the target pressure sensor, and the second time period is the period after the end time of the current fault period of the target pressure sensor; Based on the correlation between the target detection data and the detection data of various types of pressure sensors, which is related to the internal structure of the fuel cell and the gas conduction and balance process at different locations where different pressure sensors are installed, the working state of the target pressure sensor is determined; the working state of the target pressure sensor includes normal state and fault state.

2. The pressure sensor fault data analysis method according to claim 1, characterized in that, When the target pressure sensor includes the ejector inlet pressure sensor, determining the operating state of the target pressure sensor based on the correlation between the target detection data and the detection data of various types of pressure sensors includes: Based on the target detection data, the first change and the second change of the pressure detection values ​​of the anode inlet pressure sensor and the anode outlet pressure sensor in the second time period relative to the first time period are determined respectively. The operating state of the ejector inlet pressure sensor is determined based on the magnitudes of the first and second changes.

3. The pressure sensor fault data analysis method according to claim 1, characterized in that, When the target pressure sensor includes the anode inlet pressure sensor, determining the operating state of the target pressure sensor based on the correlation between the target detection data and the detection data of various types of pressure sensors includes: Based on the target detection data, a first trend of change of the pressure detection value of the ejector inlet pressure sensor during the first time period and a third change of the pressure detection value of the anode outlet pressure sensor in the second time period relative to the pressure detection value of the first time period are determined. Based on the first trend and the third change, the operating state of the anode inlet pressure sensor is determined.

4. The pressure sensor fault data analysis method according to claim 1, characterized in that, When the target pressure sensor includes the anode outlet pressure sensor, determining the operating state of the target pressure sensor based on the correlation between the target detection data and the detection data of various types of pressure sensors includes: Based on the target detection data, the second and third trends of the pressure detection values ​​of the ejector inlet pressure sensor and the anode inlet pressure sensor are determined in the first time period, and the fourth change of the pressure detection value of the anode inlet pressure sensor in the second time period relative to the pressure detection value in the first time period is determined. Based on the second trend, the third trend, and the fourth change, the operating state of the anode outlet pressure sensor is determined.

5. The pressure sensor fault data analysis method according to claim 1, characterized in that, The fault log is determined in the following way: Obtain the current target operating condition parameters of the fuel cell stack; the target operating condition parameters are output current or output power. Based on the target operating condition parameters, determine the target range of pressure detection values ​​for each pressure sensor; If the duration during which the pressure sensor's pressure detection value deviates from the target range is greater than or equal to the fault standard duration corresponding to the pressure sensor, the fault period during which the pressure sensor's pressure detection value continuously deviates from the target range is recorded to obtain the fault log.

6. A pressure sensor fault data analysis device, characterized in that, include: The acquisition module is used to acquire the fault log of the pressure sensor of the stack anode within the target time period. The pressure sensor includes at least the ejector inlet pressure sensor, the anode inlet pressure sensor, and the anode outlet pressure sensor. The first processing module is used to determine the failure frequency of each type of pressure sensor within the target time period based on the failure logs of each type of pressure sensor. The determination module is used to determine the standard duration of each type of pressure sensor based on the failure frequency of each type of pressure sensor. If the detection data of the pressure sensor deviates from the target range of the fault standard duration, the fault log of the pressure sensor is updated; based on the type of each pressure sensor, the fault standard duration corresponding to the pressure sensor, and the duration of the target time period, a frequency threshold corresponding to each pressure sensor is determined; if the fault frequency of the pressure sensor is greater than the corresponding frequency threshold, the pressure sensor is identified as the target pressure sensor. The second processing module is used to acquire target detection data of pressure sensors of other types besides the target pressure sensor in each type of pressure sensor during the first time period and the second time period; acquire all detection data of pressure sensors of other types besides the target pressure sensor in each type of pressure sensor during the first time period and the second time period; determine fault detection data of pressure sensors of other types besides the target pressure sensor in each type of pressure sensor during the first time period and the second time period based on the fault log of the pressure sensor of the stack anode during the target time period; and remove the fault detection data from all detection data of pressure sensors of other types besides the target pressure sensor in each type of pressure sensor during the first time period and the second time period to obtain the target detection data. The first time period is the period before the start time of the current fault period of the target pressure sensor, and the second time period is the period after the end time of the current fault period of the target pressure sensor; The third processing module is used to determine the operating state of the target pressure sensor based on the correlation between the target detection data and the detection data of various types of pressure sensors. The correlation is related to the internal structure of the fuel cell and the gas conduction and balance process at different locations where different pressure sensors are installed. The operating state of the target pressure sensor includes a normal state and a fault state.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the pressure sensor fault data analysis method as described in any one of claims 1 to 5.

8. A fuel cell, characterized in that, This includes fuel cell stacks and the electronic equipment as described in claim 7.

Images