Fuel cell fault early warning method, fuel cell system and vehicle

Abstract

The invention discloses a fuel cell fault early warning method, a fuel cell system and a vehicle, and relates to the technical field of fuel cells. The fuel cell fault early warning method comprises the following steps: in an operation process of a fuel cell, carrying out data acquisition on the fuel cell, and obtaining current state data of the fuel cell; obtaining a reference state data interval corresponding to the current state data according to a preset training model in the cloud; when the current state data is not in the reference state data interval, calling historical state data stored in the cloud; according to the current state data and the historical state data, the prediction time of fuel cell fault occurrence is obtained, reminding information is sent to a driver through a man-machine interaction system, and the reminding information comprises the prediction time. According to the invention, the possibility of damage of the fuel cell is reduced, the service life of the fuel cell is prolonged, and the reliability of the fuel cell is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fuel cells, and in particular to a fuel cell failure early warning method, a fuel cell system and a vehicle. Background Art

[0002] In the related art, the fault detection of fuel cell systems usually relies on real-time collected status data, and compares the acquired status data with a preset threshold value as a basis for determining whether the fuel cell system has a fault. However, the current fault detection method can often only confirm after the fuel cell system fault actually occurs, which has a lag and cannot effectively prevent the occurrence of faults or take intervention measures at the early stage of the fault, which can easily cause damage to the fuel cell system. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a fuel cell failure early warning method, which can achieve early warning of fuel cell system failure and significantly reduce the risk of damage to the fuel cell system.

[0004] The present invention also provides a vehicle controller, a fuel cell system, a vehicle, an electronic device and a computer-readable storage medium.

[0005] According to the first aspect of the present invention, the early warning method for fuel cell failure is applied to a vehicle having a fuel cell and a human-computer interaction system, wherein the vehicle is connected to the cloud for communication, and the early warning method comprises: During the operation of the fuel cell, data collection is performed on the fuel cell to obtain current state data of the fuel cell; According to the training model preset in the cloud, obtaining a reference state data interval corresponding to the current state data; When the current state data is not within the reference state data interval, calling the historical state data stored in the cloud; The predicted time of occurrence of the fuel cell failure is obtained according to the current state data and the historical state data, and a reminder message is sent to the driver through the human-computer interaction system, wherein the reminder message includes the predicted time.

[0006] The fuel cell failure early warning method according to the embodiment of the present invention has at least the following beneficial effects: The embodiment of the present invention obtains current status data and compares it with a reference status data interval. When the current status data is not within the reference status data interval, it determines that the current status data of the fuel cell deviates from the normal range; then, by calling the historical status data stored in the cloud, the predicted time of the fuel cell failure is obtained according to the current status data and the historical status data, and a reminder message is sent to the driver through the human-computer interaction system, thereby realizing early warning of fuel cell failure. Compared with confirming that the fuel cell system has failed only after the fuel cell failure actually occurs, by predicting the time when the fuel cell failure occurs, the occurrence of the failure is effectively prevented, and the driver or maintenance personnel can be reminded to take intervention measures in the early stage before and after the failure occurs, thereby reducing the possibility of fuel cell damage, thereby extending the service life of the fuel cell and increasing the reliability of the fuel cell.

[0007] According to some embodiments of the present invention, calling the historical status data stored in the cloud includes: Calling all the historical status data within a preset time period before the current moment to obtain a historical data set; Obtaining a predicted time of occurrence of the fuel cell failure according to the current state data and the historical state data, including: Determining the maximum historical state data in the historical data set; When the current state data is greater than the maximum historical state data, and the historical state data in the historical data set increases in chronological order, the interval between the corresponding moment of the maximum historical state data and the current moment is used as the predicted time. According to some embodiments of the present invention, the current state data includes multiple sample data types, and the sample data types include at least a current voltage value, a current current value, a current gas concentration value, a current temperature value, and a current humidity value. The early warning method further includes: Based on the training model, a plurality of reference thresholds corresponding one to one to the plurality of sample data types are obtained; Determining the type of the sample data in which the abnormality occurs as an abnormal parameter according to the current state data and the plurality of reference thresholds; A faulty module in the fuel cell is identified based on the abnormal parameters. According to some embodiments of the present invention, the early warning method further includes: Calculating a difference between the abnormal parameter and the reference threshold value corresponding to the abnormal parameter; When the difference is less than or equal to a preset difference threshold, determining that the failure risk level of the fuel cell is low risk; When the difference is greater than the preset difference threshold, the fault risk level is determined to be high risk.

[0008] According to some embodiments of the present invention, sending reminder information to the driver through the human-computer interaction system includes: When the fault risk level is low risk, a warning animation is displayed through the human-computer interaction system; When the fault risk level is high risk, an alarm animation is displayed and a sound alarm is played through the human-computer interaction system.

[0009] According to some embodiments of the present invention, the early warning method further includes: Clearing all the historical status data stored in the cloud at intervals of a first preset time; The sample status data of the fuel cell is acquired at intervals of a second preset time and sent to the cloud for storage as the historical status data.

[0010] The vehicle controller according to the second aspect of the present invention is applied to a vehicle having a fuel cell and a human-machine interaction system, wherein the vehicle is connected to a cloud for communication, and the vehicle controller includes: A collection module, configured to collect data from the fuel cell during operation of the fuel cell and obtain current state data of the fuel cell; an acquisition module, configured to acquire a reference state data interval corresponding to the current state data according to a training model preset in the cloud; A calling module, configured to call the historical state data stored in the cloud when the current state data is not within the reference state data interval; The execution module is configured to obtain the predicted time of occurrence of the fuel cell failure based on the current state data and the historical state data, and send a reminder message to the driver through the human-computer interaction system, wherein the reminder message includes the predicted time.

[0011] Since the vehicle controller adopts all the technical solutions of the fuel cell failure early warning method of the first embodiment, it has at least all the beneficial effects brought by the technical solutions of the above embodiments, which will not be repeated here.

[0012] According to the fuel cell system of the third embodiment of the present invention, the fuel cell failure early warning method as described in the first embodiment is applied.

[0013] The fuel cell system according to the embodiment of the present invention has at least the following beneficial effects: The fuel cell system applies the fuel cell failure early warning method of the first aspect embodiment, realizes the early warning of fuel cell system failure, effectively reduces the risk of fuel cell system failure, increases the service life of the fuel cell system, and increases the reliability and stability of the fuel cell system.

[0014] A vehicle according to an embodiment of the fourth aspect of the present invention comprises the fuel cell system described in the embodiment of the third aspect.

[0015] The vehicle according to the embodiment of the present invention has at least the following beneficial effects: The vehicle adopts the fuel cell system of the third aspect of the embodiment, and realizes early warning of fuel cell system failure by adopting a fuel cell failure early warning method, thereby effectively reducing the risk of fuel cell system failure, reducing the possibility of fuel cell damage, and increasing the service life of the fuel cell system, thereby reducing the maintenance cost of the vehicle and increasing the reliability and stability of the vehicle.

[0016] According to an embodiment of the fifth aspect of the present invention, the electronic device includes: at least one processor and at least one memory, wherein the at least one memory is used to store at least one program; when the at least one program is executed by the at least one processor, the at least one processor implements the fuel cell failure early warning method disclosed in the first aspect.

[0017] According to the computer-readable storage medium of the sixth aspect embodiment of the present invention, processor-executable instructions are stored therein, and the processor-executable instructions, when executed by the processor, are used to execute the fuel cell failure early warning method disclosed in the first aspect.

[0018] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The present invention will be further described below with reference to the accompanying drawings and embodiments, wherein: Figure 1 A flowchart of a method for early warning of a fuel cell failure according to an embodiment of the present invention; Figure 2 This is a flowchart of steps S103 and S104 in a fuel cell failure early warning method according to an embodiment of the present invention; Figure 3 A flowchart of a method for early warning of a fuel cell failure according to another embodiment of the present invention; Figure 4 A flowchart of a method for early warning of a fuel cell failure according to another embodiment of the present invention; Figure 5This is a flowchart of step S104 in the fuel cell failure early warning method according to an embodiment of the present invention; Figure 6 Schematic diagram of the structure of a vehicle controller according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0021] In the description of the present invention, it should be understood that descriptions involving orientation, such as orientation or positional relationship indicated as up, down, etc., are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0022] In the description of the present invention, "a plurality" means more than two. If there is a description of "first" or "second", it is only used for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0023] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0024] Understandably, current fault detection methods can often only confirm a fuel cell system fault after it actually occurs. This lag means that when the fuel cell system is about to reach the critical point of failure, the driver may not be notified in time and continue to drive the vehicle, which in turn causes the impact of the fault to expand, causing damage to the fuel cell system, increasing the maintenance cost of the fuel cell system, and even causing safety hazards.

[0025] To this end, some embodiments of the present invention provide a fuel cell failure early warning method, which is applied to a vehicle having a fuel cell and a human-computer interaction system, wherein the vehicle is connected to the cloud through communication. In one example, the vehicle is connected to the cloud through a network. The cloud can also be called a cloud platform or a cloud server, which can be implemented with an independent server or a server cluster consisting of multiple servers.

[0026] Reference Figure 1 As shown, in an embodiment of the present invention, the early warning method for fuel cell failure includes: Step S101 : during the operation of the fuel cell, data of the fuel cell is collected to obtain current state data of the fuel cell.

[0027] It is understandable that in the embodiment of the present invention, when the fuel cell is running, various types of operating data are generated, such as temperature, current, voltage, etc. This embodiment can obtain current state data by collecting these data in real time, and the current state data is used to characterize the state of the fuel cell at the current moment.

[0028] Specifically, in an embodiment of the present invention, the vehicle is configured with at least a temperature sensor for detecting the temperature of the fuel cell, a pressure sensor for detecting the gas pressure of the fuel cell, a flow sensor for detecting the gas flow of the fuel cell, a humidity sensor for detecting the ambient humidity of the fuel cell installation location, a concentration sensor for detecting the gas concentration of the fuel cell, etc.

[0029] Step S102, obtaining a reference state data interval corresponding to the current state data according to a training model preset in the cloud.

[0030] It should be noted that in the embodiment of the present invention, the status data collected by various sensors installed on the vehicle will be uploaded to the cloud. The preset mathematical model is learned based on the status data stored in the cloud to obtain a training model. In this embodiment, the selection of the mathematical model can be selected according to the actual situation, and this embodiment does not limit this.

[0031] Specifically, in an embodiment of the present invention, the early warning method for fuel cell failure further includes: Step S301, clearing all historical status data stored in the cloud at intervals of a first preset time.

[0032] It can be understood that in order to prevent the cloud storage space from being full and unable to store the latest historical status data, in this embodiment, after a first preset time, the system can clear all historical status data stored in the cloud, thereby avoiding saturation of the cloud and ensuring that the cloud can continue to effectively save the latest historical status data. For example, the first preset time is set to 20 hours.

[0033] In an embodiment of the present invention, the early warning method for fuel cell failure further includes: Step S302 , obtaining sample status data of the fuel cell at intervals of a second preset time, and sending the sample status data to the cloud for storage as historical status data.

[0034] In an embodiment of the present invention, during the operation of the fuel cell, data of the fuel cell is periodically collected at intervals of a second preset time to obtain sample status data, and the sample status data stored in the cloud becomes the basis for subsequent training model learning.

[0035] It is understandable that in the embodiment of the present invention, based on the preset training model, the system can obtain the reference state data interval corresponding to each parameter, and the reference state data interval is the range of various indicators that should be maintained when the fuel cell is operating normally. Taking temperature data as an example, based on the preset training model, the system can obtain the reference state data interval corresponding to the temperature data as 50°C (degrees Celsius) to 100°C (degrees Celsius). Based on this, when the current temperature value in the current state data is within this range, it means that the fuel cell is in a stable operating state and there is no obvious hidden danger of failure.

[0036] Step S103: when the current state data is not within the reference state data interval, the historical state data stored in the cloud is called.

[0037] In an embodiment of the present invention, when the current state data is not within the reference state data interval, it means that the current state data of the fuel cell has deviated from the normal range, and it can be determined that the fuel cell has an abnormality. It should be noted that the abnormality of the fuel cell does not mean that the fuel cell has failed, but only indicates that the fuel cell has a potential failure. On this basis, this embodiment calls the historical state data stored in the cloud to perform a retrospective analysis of the fuel cell state at each time point before the current moment.

[0038] Step S104, obtaining the predicted time of occurrence of fuel cell failure based on the current state data and the historical state data, and sending a reminder message to the driver through the human-computer interaction system, the reminder message including the predicted time.

[0039] In the embodiment of the present invention, by retrospectively analyzing the fuel cell status at each time point before the current moment, combined with the current status data, the change trend of the fuel cell status data over time and the possible future development trend can be confirmed. Based on the predicted development trend, the time point at which the fuel cell may fail can be predicted, that is, the predicted time is generated.

[0040] In the embodiment of the present invention, the human-computer interaction system can be a central control screen of the vehicle, a dashboard, or a head-up display device, which is not limited in this embodiment. It is understandable that when the system detects that there is a hidden danger of failure in the fuel cell and generates a time point when the failure may occur, the system can send a reminder message to the driver through the human-computer interaction system, thereby promptly notifying the driver of the current operating status of the fuel cell, reminding the driver to stop driving the vehicle, and promptly check and repair it to avoid damage to the fuel cell.

[0041] The embodiment of the present invention obtains current status data and compares it with a reference status data interval. When the current status data is not within the reference status data interval, it determines that the current status data of the fuel cell deviates from the normal range; then, by calling the historical status data stored in the cloud, the predicted time of the fuel cell failure is obtained according to the current status data and the historical status data, and a reminder message is sent to the driver through the human-computer interaction system, thereby realizing early warning of fuel cell failure. Compared with confirming that the fuel cell system has failed only after the fuel cell failure actually occurs, by predicting the time when the fuel cell failure occurs, the occurrence of the failure is effectively prevented, and the driver or maintenance personnel can be reminded to take intervention measures in the early stage before and after the failure occurs, thereby reducing the possibility of fuel cell damage, thereby extending the service life of the fuel cell, increasing the reliability of the fuel cell, and reducing the maintenance cost of the fuel cell.

[0042] Reference Figure 2 As shown, in this embodiment of the present invention, step S103 includes: Step S1031, calling all historical status data within a preset time period before the current moment to obtain a historical data set.

[0043] It is understandable that in order to predict the future development trend of the status data by the change trend of the status data within the preset time before the current moment, in the embodiment of the present invention, the system can call all the historical status data within the preset time before the current moment from the cloud. In one example, the preset time is 1 minute, and the system can call all the historical status data stored in the cloud within the past 1 minute from the cloud to form a historical data set.

[0044] In this embodiment, step S104 includes: Step S1041, determining the maximum historical state data in the historical data set.

[0045] Step S1042, when the current state data is greater than the maximum historical state data, and the historical state data in the historical data set increases in chronological order, the interval time between the corresponding moment of the maximum historical state data and the current moment is used as the prediction time.

[0046] It should be noted that the maximum historical status data is the one with the largest value among all the historical status data. Among them, when the historical status data in the historical data set shows an increasing trend in chronological order, the maximum historical status data is the historical status data obtained closest to the current moment. For the convenience of description, temperature data is used as an example. In one example, the preset duration is 1 minute, and the cloud stores historical status data of 80°C for the past 1 minute, historical status data of 90°C for the past 40 seconds, and historical status data of 100°C for the past 20 seconds. Among them, the historical status data in the historical data set shows an increasing trend, and the maximum historical status data is 100°C.

[0047] At this time, the current state data detected is 110℃, which not only exceeds the reference state data range of 50℃ (Celsius) to 100℃ (Celsius), but also exceeds the maximum historical state data of 100℃, which means that the temperature of the fuel cell is continuing to rise and tends to be out of control, and there is a serious risk of failure due to excessive temperature. It is understandable that since the current temperature data has exceeded the maximum historical state data and considering the previous upward trend, the system can reasonably infer that the temperature of the fuel cell is likely to continue to rise in this growth trend.

[0048] Based on this logic, the system can use the time difference (20 seconds) between the collection time of the maximum historical status data (i.e., 100°C) and the current time as a reference for the prediction time, thereby predicting that within the next 20 seconds, the fuel cell may fail due to excessive temperature.

[0049] Reference Figure 3 As shown, in this embodiment of the present invention, the early warning method further includes: Step S201, based on the training model, obtain multiple reference thresholds corresponding to multiple sample data types.

[0050] It is understandable that in the embodiment of the present invention, the current state data includes multiple sample data types, and multiple reference thresholds can be obtained based on the training model, wherein the multiple reference thresholds correspond to the multiple sample data types one by one. In this embodiment, the sample data types include at least the current voltage value, the current current value, the current gas concentration value, the current temperature value, and the current humidity value, based on which the reference thresholds include at least the current voltage threshold, the current current threshold, the current gas concentration threshold, the current temperature threshold, and the current humidity threshold.

[0051] Step S202: Determine the type of abnormal sample data as an abnormal parameter based on the current state data and multiple reference thresholds.

[0052] In an embodiment of the present invention, when the sample data is greater than the corresponding reference threshold, the sample data type is determined to be abnormal, and its sample parameter is an abnormal parameter. In an example, the current temperature is 130°C, and the current temperature threshold is 120°C. Therefore, the current temperature value is an abnormal sample data type, and the abnormal parameter is 130°C.

[0053] Step S203, confirming the faulty module in the fuel cell according to the abnormal parameters.

[0054] It should be noted that, as a complex system, a fuel cell integrates multiple functional modules, including but not limited to an energy submodule, a circuit submodule, and a monitoring module, etc. The operating status of the multiple functional modules can be reflected by the sample data of each sample data type.

[0055] For example, hydrogen concentration is directly related to hydrogen management in the energy submodule, and voltage value is directly related to hydrogen management in the energy submodule, etc. When the system detects an abnormality in a specific sample data type, it can quickly locate the corresponding functional module, accurately trace the hidden fault, simplify the diagnosis process of maintenance personnel, eliminate the need for tedious troubleshooting, reduce the maintenance difficulty of maintenance personnel, and improve the maintenance efficiency of fuel cells.

[0056] Reference Figure 4 As shown, in this embodiment of the present invention, the early warning method further includes: Step S204: Calculate the difference between the abnormal parameter and the reference threshold value corresponding to the abnormal parameter.

[0057] Step S205: when the difference is less than or equal to the preset difference threshold, it is determined that the failure risk level of the fuel cell is low risk.

[0058] Step S206: when the difference is greater than a preset difference threshold, the fault risk level is determined to be high risk.

[0059] For the convenience of description, temperature data is used as an example. In one example, it is assumed that the detected abnormal parameter is 130°C, and the reference threshold corresponding to the temperature parameter is set to 120°C. After calculation, it is found that the difference between the two is 10°C. In this embodiment, the preset difference threshold is set to 20°C, and the difference between the abnormal parameter and the reference threshold does not exceed the preset difference threshold. Therefore, the system can determine that the failure risk level of the fuel cell is low risk.

[0060] In another example, assume that the detected abnormal parameter is 150°C, and the reference threshold corresponding to the temperature parameter is set to 120°C. After calculation, it is found that the difference between the two is 30°C. In this embodiment, the preset difference threshold is set to 20°C, and the difference between the abnormal parameter and the reference threshold exceeds the preset difference threshold. Therefore, the system can determine that the failure risk level of the fuel cell is high risk.

[0061] Reference Figure 5 As shown, in this embodiment of the present invention, step S104 further includes: Step S1043: when the fault risk level is low risk, a warning animation is displayed through the human-computer interaction system.

[0062] Step S1044: when the fault risk level is high risk, an alarm animation is displayed and a sound alarm is played through the human-computer interaction system.

[0063] It is understandable that in the embodiment of the present invention, when the fault risk level is low risk, it means that although the fuel cell has an abnormal situation and there is a possibility of failure within a period of time, the urgency of the failure is relatively low. Therefore, when the fault risk level is low risk, this embodiment only displays a warning animation through the human-computer interaction system to intuitively convey to the driver the information that the fuel cell has a potential failure within a period of time, so that the driver can have enough time to react and take necessary preventive measures within a period of time. In one example, the human-computer interaction system is a display screen of an instrument panel or a central control car machine, and the warning animation can be a flashing indicator light or a text pop-up warning, which is not limited in this embodiment.

[0064] In an embodiment of the present invention, when the fault risk level is high risk, it means that there is an abnormality in the fuel cell and there is a possibility of an imminent failure, that is, the urgency of the failure is relatively high. Therefore, in this embodiment, when the fault risk level is high risk, the human-computer interaction system displays an alarm animation and plays a sound alarm at the same time, thereby intuitively conveying to the driver that the fuel cell is about to fail, so that the driver can stop driving immediately to avoid further damage to the fuel cell. It should be noted that in this embodiment, the alarm animation is a more intense and eye-catching reminder screen than the early warning animation. For example, the alarm animation can be a high-frequency flashing of the entire dashboard screen. In this embodiment, the human-computer interaction system can also be a sound, and the sound alarm can be a periodic beep.

[0065] This embodiment provides both visual and audible reminders, forming a dual visual and audible warning, ensuring that the driver can immediately perceive the information that the fuel cell is about to fail and take necessary preventive measures immediately, while effectively distinguishing between high and low risk level reminder methods.

[0066] Reference Figure 6 As shown, an embodiment of the present invention further provides a vehicle controller 600, which is applied to a vehicle having a fuel cell and a human-machine interaction system, and the vehicle is connected to the cloud for communication. The vehicle controller 600 includes: The acquisition module 601 is configured to acquire data of the fuel cell during the operation of the fuel cell and obtain current state data of the fuel cell.

[0067] The acquisition module 602 is configured to acquire a reference state data interval corresponding to the current state data according to a training model preset in the cloud.

[0068] The calling module 603 is configured to call the historical state data stored in the cloud when the current state data is not within the reference state data interval.

[0069] The execution module 604 is configured to obtain the predicted time of occurrence of the fuel cell failure according to the current state data and the historical state data, and send a reminder message to the driver through the human-computer interaction system, wherein the reminder message includes the predicted time.

[0070] Since the vehicle controller 600 adopts all the technical solutions of the fuel cell failure early warning method of the above-mentioned embodiment, it has at least all the beneficial effects brought by the technical solutions of the above-mentioned embodiment, which will not be repeated here.

[0071] It should be noted that, in the embodiment of the present invention, the acquisition module 601 can also execute steps S301 to S302 in the above embodiment; the calling module 603 can also execute step S1031 in the above embodiment; the execution module 604 can also execute steps S1041 to S1042, steps S201 to S203, steps S204 to S206 and steps S1043 to S1044 in the above embodiment.

[0072] The embodiment of the present invention also provides a fuel cell system, which applies the fuel cell failure early warning method of the above embodiment, and is suitable for vehicles. It can be understood that this embodiment realizes the early warning of fuel cell system failure, effectively reduces the risk of fuel cell system failure, increases the service life of the fuel cell system, and increases the reliability and stability of the fuel cell system.

[0073] The embodiment of the present invention further provides a vehicle, including the fuel cell system of the above embodiment. Specifically, in the embodiment of the present invention, the vehicle can be a private car, such as a sedan, SUV, MPV or pickup truck. The vehicle can also be an operating vehicle, such as a van, bus, small truck or large trailer.

[0074] It can be understood that the vehicle of this embodiment achieves early warning of fuel cell system failure by adopting a fuel cell failure early warning method, effectively reducing the risk of fuel cell system failure, reducing the possibility of fuel cell damage, and increasing the service life of the fuel cell system, thereby reducing the maintenance cost of the vehicle and increasing the reliability and stability of the vehicle.

[0075] An embodiment of the present invention further provides an electronic device, the electronic device comprising: at least one processor; at least one memory for storing at least one program; When at least one program is executed by at least one processor, the above-mentioned fuel cell failure early warning method is implemented.

[0076] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program executable by a processor is stored. When the computer program executable by the processor is executed by the processor, it is used to implement the above-mentioned fuel cell failure early warning method.

[0077] The terms "first", "second", "third", "fourth", etc. (if any) in the description of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can, for example, be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0078] It should be understood that in the present invention, "at least one (item)" refers to one or more, and "plurality" refers to two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can represent: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0079] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0080] In the embodiments of the present invention, the term "module" or "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0081] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0082] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0083] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Acce Memory, referred to as RAM), disk or optical disk and other media that can store program codes.

[0084] The step numbers in the above method embodiment are only provided for the convenience of explanation and description, and no limitation is imposed on the order of the steps. The execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

Claims

1. A fuel cell failure early warning method, characterized in that: Applied to a vehicle having a fuel cell and a human-machine interaction system, the vehicle being connected to a cloud for communication, the early warning method comprises: During the operation of the fuel cell, data collection is performed on the fuel cell to obtain current state data of the fuel cell; According to the training model preset in the cloud, obtaining a reference state data interval corresponding to the current state data; When the current state data is not within the reference state data interval, calling the historical state data stored in the cloud; The predicted time of occurrence of the fuel cell failure is obtained according to the current state data and the historical state data, and a reminder message is sent to the driver through the human-computer interaction system, wherein the reminder message includes the predicted time.

2. The fuel cell failure early warning method according to claim 1, characterized in that: The calling of the historical status data stored in the cloud includes: Calling all the historical status data within a preset time period before the current moment to obtain a historical data set; Obtaining a predicted time of occurrence of the fuel cell failure according to the current state data and the historical state data, including: Determining the maximum historical state data in the historical data set; When the current state data is greater than the maximum historical state data, and the historical state data in the historical data set increases in chronological order, the interval between the corresponding moment of the maximum historical state data and the current moment is used as the predicted time.

3. The fuel cell failure early warning method according to claim 1, characterized in that: The current state data includes a plurality of sample data types, and the sample data types include at least a current voltage value, a current current value, a current gas concentration value, a current temperature value, and a current humidity value. The early warning method further includes: Based on the training model, a plurality of reference thresholds corresponding one to one to the plurality of sample data types are obtained; Determining the type of the sample data in which the abnormality occurs as an abnormal parameter according to the current state data and the plurality of reference thresholds; A faulty module in the fuel cell is identified based on the abnormal parameters.

4. The fuel cell failure early warning method according to claim 3, characterized in that: The early warning method also includes: Calculating a difference between the abnormal parameter and the reference threshold value corresponding to the abnormal parameter; When the difference is less than or equal to a preset difference threshold, determining that the failure risk level of the fuel cell is low risk; When the difference is greater than the preset difference threshold, the fault risk level is determined to be high risk.

5. The fuel cell failure early warning method according to claim 4, characterized in that: The sending of reminder information to the driver through the human-computer interaction system includes: When the fault risk level is low risk, a warning animation is displayed through the human-computer interaction system; When the fault risk level is high risk, an alarm animation is displayed and a sound alarm is played through the human-computer interaction system.

6. The fuel cell failure early warning method according to claim 1, characterized in that: The early warning method also includes: Clearing all the historical status data stored in the cloud at intervals of a first preset time; The sample status data of the fuel cell is acquired at intervals of a second preset time and sent to the cloud for storage as the historical status data.

7. A vehicle controller, characterized in that: Applicable to a vehicle having a fuel cell and a human-machine interaction system, the vehicle is connected to the cloud for communication, and the vehicle controller includes: A collection module, configured to collect data from the fuel cell during operation of the fuel cell and obtain current state data of the fuel cell; an acquisition module, configured to acquire a reference state data interval corresponding to the current state data according to a training model preset in the cloud; A calling module, configured to call the historical state data stored in the cloud when the current state data is not within the reference state data interval; The execution module is configured to obtain the predicted time of occurrence of the fuel cell failure based on the current state data and the historical state data, and send a reminder message to the driver through the human-computer interaction system, wherein the reminder message includes the predicted time.

8. A fuel cell system, characterized in that: The fuel cell failure early warning method according to any one of claims 1 to 6 is applied.

9. A vehicle, characterized in that: Comprising a fuel cell system as claimed in claim 8.

10. An electronic device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the fuel cell failure early warning method according to any one of claims 1 to 6.

11. A computer-readable storage medium storing instructions executable by a processor, characterized in that: The processor-executable instructions are used to execute the fuel cell failure early warning method according to any one of claims 1 to 6 when executed by the processor.

Images