Hydrogen leakage control method, electronic equipment and vehicle

Abstract

The invention provides a hydrogen leakage control method, electronic equipment and a vehicle, and the method comprises the steps: determining a hydrogen concentration sequence corresponding to each hydrogen-related region based on the hydrogen concentration data of a plurality of hydrogen-related regions of the vehicle; when the hydrogen concentration sequences of the plurality of hydrogen-related regions meet abnormal conditions, determining a target sequence corresponding to each hydrogen-related region in the time range from the hydrogen concentration sequences; based on the target sequence of each hydrogen-related region and the quantitative relationship between the target sequences of any two hydrogen-related regions, determining corresponding feature data of each hydrogen-related region in the time range; based on the feature data, determining a risk area and a confidence coefficient corresponding to the risk area from the plurality of hydrogen-related areas by using a leakage identification model; determining a leakage area from the risk area based on the confidence coefficient; and under the condition that the hydrogen concentration data of the leakage area is greater than a preset concentration threshold value, executing a target control strategy corresponding to the leakage area. According to the invention, the timeliness of controlling the hydrogen leakage of the vehicle can be improved.

Description

Technical Field

[0001] This application belongs to the field of vehicle engineering and relates to hydrogen leakage control technology, and more particularly to a hydrogen leakage control method, electronic equipment and vehicle. Background Technology

[0002] With the development of new energy vehicles, hydrogen fuel cell vehicles, as a new type of transportation, are seeing a gradual increase in their ownership. Consequently, safety issues related to the use of hydrogen fuel cell vehicles have also attracted attention. Since hydrogen fuel cell vehicles typically store energy through multiple high-pressure gaseous hydrogen storage tanks, hydrogen fuel leakage poses a potential safety risk. Currently, hydrogen concentration sensors are commonly installed in the vehicle for hydrogen fuel detection.

[0003] However, this method cannot promptly identify the location of the leak, and the location of the hydrogen leak area is inaccurate, which can easily lead to the problem of low timeliness in handling hydrogen leak accidents. Summary of the Invention

[0004] In view of the above, it is necessary to propose a hydrogen leakage control method, electronic equipment, and vehicle to solve the technical problem of untimely handling of hydrogen leakage accidents in hydrogen-powered vehicles.

[0005] This application provides a hydrogen leakage control method, the method comprising: determining a hydrogen concentration sequence corresponding to each hydrogen-related area based on hydrogen concentration data of multiple hydrogen-related areas of a vehicle within a preset period; when the hydrogen concentration sequences of the multiple hydrogen-related areas meet preset abnormal conditions, determining a target sequence corresponding to each hydrogen-related area within a preset time range from the hydrogen concentration sequences; determining feature data corresponding to each hydrogen-related area within the time range based on the target sequence of each hydrogen-related area and the quantitative relationship between the target sequences of any two hydrogen-related areas; determining risk areas and corresponding confidence levels of the risk areas from the multiple hydrogen-related areas based on the feature data using a preset leakage identification model; wherein the leakage identification model is trained by area information corresponding to the multiple hydrogen-related areas, test fluid data of the multiple hydrogen-related areas, and environmental information of the environment in which the vehicle is located; determining leakage areas from the risk areas based on the confidence levels; and executing a target control strategy corresponding to the leakage area when the hydrogen concentration data of the leakage area is greater than a preset concentration threshold.

[0006] In some embodiments, the abnormal conditions include any one or more of the following combinations: the hydrogen concentration sequence of any hydrogen-related region indicates that the hydrogen concentration of the hydrogen-related region has an upward trend within the preset period; the hydrogen concentration sequence of any hydrogen-related region indicates that the change in hydrogen concentration is greater than a preset gradient threshold; the maximum value of the hydrogen concentration indicated by the hydrogen concentration sequences corresponding to the plurality of hydrogen-related regions is greater than a preset base concentration.

[0007] In some embodiments, determining the feature data corresponding to each hydrogen-related region within the time range based on the target sequence of each hydrogen-related region and the quantitative relationship between the target sequences of any two hydrogen-related regions includes: determining first feature data for each hydrogen-related region based on the target sequence of each hydrogen-related region; the first feature data includes the hydrogen concentration rise rate, hydrogen concentration rise time constant, hydrogen concentration peak value, and hydrogen concentration integral; determining second feature data for any two hydrogen-related regions based on the target sequences of any two hydrogen-related regions; the second feature data includes the response delay difference, peak value difference, and ratio of the hydrogen concentration of the two hydrogen-related regions; and standardizing the first feature data and the second feature data to obtain feature data.

[0008] In some embodiments, determining the leakage area from the risk areas based on the confidence level includes: determining the difference between the confidence levels of any two risk areas; and if the difference is higher than a preset difference threshold, determining the risk area corresponding to the larger confidence level as the leakage area.

[0009] In some embodiments, determining the leakage area from the risk area based on the confidence level includes: when the difference between the confidence levels of any two risk areas is less than or equal to the difference threshold, outputting the confidence level of the risk area multiple times using the leakage identification model; selecting the maximum confidence level from each output confidence level of the leakage identification model, and using the risk area corresponding to the maximum confidence level as a candidate area to obtain multiple candidate areas corresponding to the multiple outputs; and selecting the risk area with the highest frequency of occurrence from the multiple candidate areas as the leakage area.

[0010] In some embodiments, the method further includes: when the hydrogen concentration data in the leak area is less than or equal to the concentration threshold, controlling the vehicle to output a preset alarm message; the alarm message includes any one or more combinations of visual information, sound information, and text information.

[0011] In some embodiments, the method further includes: after executing the target control strategy corresponding to the leak area, if the hydrogen concentration in the leak area shows a decreasing trend and the hydrogen concentration is less than a safety threshold, controlling the vehicle to output reset request information.

[0012] In some embodiments, the method further includes: training the leak identification model, including: determining the leak characteristics of the vehicle based on the regional information corresponding to the plurality of hydrogen-related areas, the test fluid data of the plurality of hydrogen-related areas, and the environmental information of the environment in which the vehicle is located; the leak characteristics are used to indicate the hydrogen leak pattern of the plurality of hydrogen-related areas; based on the leak characteristics, determining the predicted confidence level of each hydrogen-related area using a preset initial identification model; updating the initial identification model based on the difference between the predicted confidence level and the leak probability of the pre-labeled plurality of hydrogen-related areas; stopping the updating of the initial identification model when the difference meets a preset termination condition, thereby obtaining a leak identification model trained to a convergent state.

[0013] This application also provides an electronic device, which includes: a memory storing at least one instruction; and a processor executing the instructions stored in the memory to implement the hydrogen leakage control method.

[0014] This application also provides a vehicle, which includes the electronic device.

[0015] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the hydrogen leakage control method.

[0016] As can be seen from the above technical solutions, the embodiments of this application achieve leak area-level localization by performing feature recognition on the time series of hydrogen concentrations at multiple points, and execute a complete closed-loop safety method with differentiated active control based on different leak locations. This improves the vehicle's early identification capability, positioning accuracy, and active safety control level for hydrogen leaks. Specifically, multiple hydrogen concentration sensors installed in the vehicle detect hydrogen concentration data in multiple hydrogen-related areas in real time, and identify the hydrogen leak area based on the sequence characteristics of concentration changes. This enables the identification of small, low-flow steady-state leaks. Compared to a single concentration over-limit alarm method, this application can detect potential leaks in the early stages of hydrogen leaks, preventing the leak from spreading. The specific area where the hydrogen leak occurs is determined based on a pre-trained leak identification model, making the control action localized and precise. Combining the area identification results with the corresponding active control strategy reduces the risk of misoperation due to unclear hydrogen leak location judgment, achieves leak area-level localization control, and enhances safety and response accuracy. Different control strategies are set for different leakage areas, and different execution priorities are set for different levels of leakage events. This improves vehicle safety and avoids a one-size-fits-all power interruption, so that the vehicle remains available in the event of a failure. Attached Figure Description

[0017] Figure 1 This is an application scenario diagram of a hydrogen leakage control method provided in an embodiment of this application.

[0018] Figure 2 This is a flowchart of a hydrogen leakage control method provided in an embodiment of this application.

[0019] Figure 3 This is a flowchart of a method for determining feature data corresponding to each hydrogen-related region according to an embodiment of this application.

[0020] Figure 4 This is a flowchart of a method for training a leak identification model according to an embodiment of this application.

[0021] Figure 5 This is a flowchart of a method for determining a leakage area based on confidence level according to an embodiment of this application.

[0022] Figure 6 This is a flowchart of a method for determining a leakage area based on confidence level, provided in another embodiment of this application.

[0023] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0024] To better understand the purpose, features, and advantages of this application, a detailed description of the application is provided below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of this application can be combined with each other. Numerous specific details are set forth in the following description to provide a thorough understanding of this application; the described embodiments are only a part of the embodiments of this application, and not all of them.

[0025] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0027] This application provides a hydrogen leakage control method that can be applied to one or more electronic devices. An electronic device is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0028] Electronic devices can be any electronic product that allows human-computer interaction with a customer, such as personal computers, tablets, smartphones, personal digital assistants (PDAs), game consoles, interactive network television (IPTV), smart wearable devices, etc.

[0029] Electronic devices may also include network devices and / or client devices. The network devices include, but are not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of hosts or network servers.

[0030] The networks in which electronic devices are located include, but are not limited to, the Internet, wide area networks, metropolitan area networks, local area networks, and virtual private networks (VPNs).

[0031] like Figure 1 The diagram illustrates an application scenario of a hydrogen leakage control method according to an embodiment of this application. This method can be applied to an electronic device 100. The electronic device 100 is installed in a vehicle 200 and is communicatively connected to vehicle components 300 within the vehicle 200. The vehicle components 300 include vehicle sensors 310 and a vehicle hydrogen energy management device 320.

[0032] Among them, sensor 310 is used to detect hydrogen concentration data in the hydrogen-related area of ​​vehicle 200 in real time.

[0033] Among them, the hydrogen energy management equipment 320 is used to control the start-up, shutdown and opening / closing of the hydrogen transmission pipeline in the hydrogen-related area of ​​the vehicle 200.

[0034] In this application, the electronic device 100 is used to receive hydrogen concentration data of different hydrogen-related areas of the vehicle 200 collected in real time by the sensor 310. Specifically, when the vehicle 200 is stationary (e.g., parked, waiting for hydrogen refueling, maintenance, etc.), multiple sensors 310 continuously collect the volume fraction of hydrogen concentration in different areas of the vehicle 200. The electronic device 100 reads the data collected by the sensor 310 at a fixed sampling period.

[0035] Electronic device 100 compares the hydrogen concentration value collected in real time by sensor 310 with the baseline concentration to determine whether there is a potential risk of hydrogen leakage in vehicle 200. When the hydrogen concentration sequence in the hydrogen-exposed area of ​​vehicle 200 meets preset conditions, it indicates that the hydrogen concentration data collected by sensor 310 shows a significant trend, thus confirming that there is a potential risk of hydrogen leakage in vehicle 200.

[0036] Electronic device 100 determines the target sequence corresponding to each hydrogen-related region within a preset time range from the hydrogen concentration sequence. Based on the target sequence of each hydrogen-related region and the quantitative relationship between the target sequences of any two hydrogen-related regions, characteristic data corresponding to each hydrogen-related region within the time range is determined. This characteristic data can indicate the pattern of hydrogen leakage present in vehicle 200.

[0037] The electronic device 100 also inputs feature data into a preset leak identification model to determine risk areas and corresponding confidence levels from multiple hydrogen-related areas, and determines leak areas from the risk areas based on the confidence levels.

[0038] If the hydrogen concentration data in the leak area is greater than the preset concentration threshold, the electronic device 100 controls the hydrogen energy management device 320 to execute the target control strategy corresponding to the leak area.

[0039] like Figure 2 The diagram shown is a flowchart of a hydrogen leakage control method according to an embodiment of this application. The order of steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements. The hydrogen leakage control method provided in this embodiment includes the following steps.

[0040] S20 determines the hydrogen concentration sequence for each hydrogen-related area based on hydrogen concentration data from multiple hydrogen-related areas of the vehicle within a preset period.

[0041] In one embodiment of this application, sensors can be used to collect hydrogen concentration data of a vehicle in real time. When the vehicle is stationary (e.g., parked, waiting for hydrogen refueling, maintenance, etc.), multiple hydrogen concentration sensors continuously collect the volume fraction of hydrogen concentration in different areas of the vehicle body. Sensor data is read at fixed intervals, and a controllable sliding time window is maintained in memory to store recent concentration changes. The hydrogen concentration sensors in the vehicle continuously collect hydrogen concentration data in hydrogen-exposed areas according to a preset sampling period. The collected real-time hydrogen concentration data is cached chronologically, forming a hydrogen concentration sequence composed of hydrogen concentration data from different times within the sliding time window, and transmitted to electronic devices via the vehicle's communication bus. The electronic devices can be the vehicle's controller or identification unit; this application does not limit their use.

[0042] In one embodiment of this application, the electronic device also manages the baseline concentration of the vehicle. Specifically, the controller of the electronic device records the baseline concentration and dynamically determines whether the current value is abnormally high; if the hydrogen concentration of all sensors remains at a long-term low level, the system remains in standby mode and does not trigger the subsequent leak area analysis process.

[0043] In one embodiment of this application, when dividing the hydrogen-related areas in a vehicle, the actual layout of hydrogen system components, pipeline routing, and cabin structure are used as the basis. Following the principle of grouping components with similar functions and relatively concentrated spaces into the same area, the spaces where hydrogen is likely to accumulate after a leak are identified as hydrogen-related areas. For example, locations above equipment with a potential hydrogen leak, or enclosed corners.

[0044] For example, the hydrogen-related area may include a refueling area, a front / rear hydrogen cylinder area, a multi-cylinder stack area, a pressure reducing valve area, pipe connections, and a fuel cell area. The refueling area may include the vehicle's hydrogen refueling port, the refueling port valve body, and the surrounding space. The front / rear hydrogen cylinder area may include the front or rear hydrogen storage cylinders, their valves, connecting pipes, etc. The multi-cylinder stack area indicates a separate hydrogen cylinder area for each stack when three or more cylinders are arranged. The pressure reducing valve area indicates the area centered on the pressure reducing valve, its inlet and outlet pipes, and the surrounding space. The pipe connection area indicates the area with concentrated soft and hard connections and joints in the pipeline between the pressure reducing valve and the fuel cell stack. The fuel cell area may be the fuel cell stack itself and its surrounding space.

[0045] In this application, the purpose of dividing the hydrogen-related areas of the vehicle is to make each leakage area correspond to a specific active control strategy and to facilitate the leakage identification model to learn the characteristics of each area.

[0046] S21, when the hydrogen concentration sequences of the multiple hydrogen-related regions meet the preset abnormal conditions, determine the target sequence corresponding to each hydrogen-related region within a preset time range from the hydrogen concentration sequences.

[0047] In one embodiment of this application, the electronic device compares the current hydrogen concentration values ​​collected in real time by each sensor with the background concentration to determine whether there is a potential hydrogen leak in the vehicle. When the hydrogen concentration sequence of multiple hydrogen-related areas meets preset abnormal conditions, it can be determined that there is a potential hydrogen leak in the vehicle. For example, if the hydrogen concentration collected by any sensor shows an upward trend within a preset time, or if the hydrogen concentration collected by any sensor exceeds a certain multiple of the base concentration, it is determined that there is a suspected leak event in the vehicle; if the concentrations of all sensors remain at a low level for a certain period of time and change slowly, it is determined that no hydrogen leak event has occurred in the vehicle, and the vehicle system can only perform basic monitoring without triggering the hydrogen leak identification model.

[0048] The abnormal conditions include any one or more of the following combinations: the hydrogen concentration sequence of any hydrogen-related region indicates that the hydrogen concentration of the hydrogen-related region has an upward trend within the preset period; the hydrogen concentration sequence of any hydrogen-related region indicates that the change in hydrogen concentration is greater than a preset gradient threshold; the maximum value of the hydrogen concentration indicated by the hydrogen concentration sequences corresponding to the multiple hydrogen-related regions is greater than a preset base concentration.

[0049] In the process of identifying hydrogen leaks in vehicles, when the hydrogen concentration sequence in a hydrogen-related area meets preset conditions, indicating a significant trend in the hydrogen concentration data collected by any sensor, it can be determined that the vehicle has a potential hydrogen leak. Specifically, when detecting abnormal fluctuations in hydrogen concentration, if the hydrogen concentration in any hydrogen-related area collected by any sensor shows an upward trend within a preset period, it indicates that the hydrogen concentration in that area or adjacent areas is abnormal, and a hydrogen leak event may occur. If the instantaneous gradient of the hydrogen concentration in any hydrogen-related area collected by any sensor exceeds a preset threshold, it indicates that the hydrogen concentration in that area or adjacent areas is abnormal, and a hydrogen leak event may occur. If the maximum value of the hydrogen concentration indicated by the hydrogen concentration sequence of multiple hydrogen-related areas exceeds the baseline concentration, for example, if the maximum value of the hydrogen concentration exceeds three times the baseline concentration, it indicates that the hydrogen concentration in multiple hydrogen-related areas of the vehicle is abnormal, and a hydrogen leak event may occur in the vehicle.

[0050] In one embodiment of this application, when it is determined that a vehicle may have a hydrogen leak, the electronic device extracts a target sequence containing the initial stage of the leak from a preset time range in the hydrogen concentration sequence, and performs feature extraction based on the hydrogen concentration sequence within the time range to obtain the feature vector corresponding to the offline stage of the electronic device. The feature vector is then input into the leak identification model to obtain the hydrogen leak area of ​​the vehicle and the corresponding confidence level.

[0051] S22, based on the target sequence of each hydrogen-related region and the quantitative relationship between the target sequences of any two hydrogen-related regions, determine the feature data corresponding to each hydrogen-related region within the time range.

[0052] In one embodiment of this application, when determining the characteristic data corresponding to each hydrogen-related region within a time range, hydrogen concentration data for the most recent period (e.g., 5–20 s) can be extracted from the hydrogen concentration sequence corresponding to each hydrogen-related region based on a preset time window to obtain the target sequence for each hydrogen-related region.

[0053] In one embodiment of this application, first feature data corresponding to each hydrogen-related region can be determined based on a target sequence for each hydrogen-related region. The first feature data includes the hydrogen concentration rise rate, the hydrogen concentration rise time constant, the hydrogen concentration peak value, and the hydrogen concentration integral. Specifically, a target sequence with a time range of 5 to 20 seconds can be extracted from the hydrogen concentration sequence collected by each sensor, and the hydrogen concentration rise rate, hydrogen concentration rise time constant, hydrogen concentration peak value, and hydrogen concentration integral corresponding to the hydrogen-related region to which the sensor belongs can be determined based on this target sequence.

[0054] In one embodiment of this application, second feature data of any two hydrogen-related regions can be determined based on target sequences of any two hydrogen-related regions. The second feature data includes the response delay difference, peak difference, and ratio of hydrogen concentration between the two hydrogen-related regions.

[0055] In one embodiment of this application, in order to improve the accuracy of subsequent prediction of the leakage area based on the first feature and the second feature, the first feature data and the second feature data can be standardized to obtain feature data, thereby eliminating the dimensional difference between the first feature and the second feature and avoiding errors in the output results of the leakage identification model due to excessive dimensional difference.

[0056] In one embodiment of this application, the specific method for determining the feature data corresponding to each hydrogen-related region can be found in [link to relevant documentation]. Figure 3 The corresponding detailed explanation.

[0057] S23, based on the feature data, a preset leak identification model is used to determine the risk area and the confidence level corresponding to the risk area from the multiple hydrogen-related areas; wherein, the leak identification model is trained by the area information corresponding to the multiple hydrogen-related areas, the test fluid data of the multiple hydrogen-related areas, and the environmental information of the environment in which the vehicle is located.

[0058] In one embodiment of this application, feature data can be input into a preset leak identification model, and the leak identification model can be used to identify hydrogen leak patterns in hydrogen-related areas indicated by the feature data, and risk areas and corresponding confidence levels can be determined from multiple hydrogen-related areas.

[0059] For example, when there are 10 hydrogen-related areas, the output of the leak identification model may include [Hydrogen-related area 1, 0; Hydrogen-related area 2, 90%; Hydrogen-related area 3, 0; Hydrogen-related area 4, 70%; Hydrogen-related area 5, 0; Hydrogen-related area 6, 80%; Hydrogen-related area 7, 0; Hydrogen-related area 8, 60%; Hydrogen-related area 9, 0; Hydrogen-related area 10, 90%]. This output indicates that the confidence level for hydrogen-related area 1 as a risk area is 0%, the confidence level for hydrogen-related area 2 as a risk area is 90%, the confidence level for hydrogen-related area 3 as a risk area is 0%, the confidence level for hydrogen-related area 4 as a risk area is 70%, the confidence level for hydrogen-related area 5 as a risk area is 0%, the confidence level for hydrogen-related area 6 as a risk area is 80%, the confidence level for hydrogen-related area 7 as a risk area is 0%, the confidence level for hydrogen-related area 8 as a risk area is 60%, the confidence level for hydrogen-related area 9 as a risk area is 0%, and the confidence level for hydrogen-related area 10 as a risk area is 90%.

[0060] Specifically, if the confidence level for any hydrogen-related area is 0, it indicates that no hydrogen leakage event has occurred in that area; if the confidence level for any hydrogen-related area is not 0, it indicates that a hydrogen leakage event may occur in that area, and thus that hydrogen-related area can be considered a risk area.

[0061] In one embodiment of this application, in order to improve the performance of the leak identification model and thus improve the accuracy of the leak identification model in screening risk areas from hydrogen-related areas, the leak identification model can be trained based on the regional information corresponding to multiple hydrogen-related areas, the test fluid data of the multiple hydrogen-related areas, and the environmental information of the vehicle's environment, so as to improve the leak identification model's ability to analyze feature data.

[0062] Specifically, the leakage characteristics of the vehicle can be determined based on the regional information corresponding to multiple hydrogen-related areas, the test fluid data of the multiple hydrogen-related areas, and the environmental information of the environment in which the vehicle is located. The leakage characteristics are used to indicate the hydrogen leakage pattern of the multiple hydrogen-related areas. Based on the leakage characteristics, the predicted confidence level of each hydrogen-related area is determined using a preset initial identification model. Based on the difference between the predicted confidence level and the leakage probability of the pre-labeled multiple hydrogen-related areas, the initial identification model is updated. When the difference meets a preset termination condition, the update of the initial identification model is stopped, and a leakage identification model trained to a convergent state is obtained.

[0063] Specifically, the greater the difference between the predicted confidence level and the leakage probability of multiple pre-labeled hydrogen-related areas, the lower the accuracy of the predicted confidence level predicted by the initial identification model. In this case, the initial identification model can be continuously updated, and the predicted confidence levels corresponding to multiple hydrogen-related areas can be output multiple times using the initial identification model. Conversely, the greater the difference between the predicted confidence level and the leakage probability of multiple pre-labeled hydrogen-related areas, the higher the accuracy of the predicted confidence level predicted by the initial identification model. In this case, the higher the similarity between the predicted confidence level and the leakage probability of multiple pre-labeled hydrogen-related areas, the more certain that the initial identification model has been trained to a convergent state, and the leakage identification model can be obtained.

[0064] In one embodiment of this application, the specific method for training the leak detection model can be found in [link to relevant documentation]. Figure 4 The corresponding detailed explanation.

[0065] S24, Based on the confidence level, determine the leakage area from the risk area.

[0066] In one embodiment of this application, after the leak identification model outputs one or more risk areas and their corresponding confidence levels, a leak area can be determined from the risk areas based on the confidence level threshold. For example, the leak area may include any combination of one or more areas such as the "front hydrogen tank area" or the "pressure reducing valve area".

[0067] In one embodiment of this application, if the difference between the confidence levels of any two risk areas is higher than the difference threshold, it indicates that the probability of a hydrogen leakage event in the risk area corresponding to the higher confidence level is the highest among all risk areas. Therefore, the risk area corresponding to the higher confidence level can be determined as the leakage area.

[0068] For example, if the difference between the confidence levels corresponding to the "front hydrogen tank area" and the "pressure reducing valve area" is higher than the difference threshold, then if the confidence level corresponding to the "front hydrogen tank area" is higher than the confidence level corresponding to the "pressure reducing valve area", then the "front hydrogen tank area" can be determined as a leaking area.

[0069] In one embodiment of this application, if the difference between the confidence levels of all risk regions is small, that is, the difference between the confidence levels of any two risk regions is less than or equal to the difference threshold, the confidence level of the risk region can be output multiple times using the leakage identification model; the maximum confidence level is selected from the confidence level output by the leakage identification model each time, and the risk region corresponding to the maximum confidence level is taken as the candidate region, so as to obtain multiple candidate regions corresponding to multiple outputs; finally, the risk region with the highest frequency of occurrence can be selected as the leakage region from the multiple candidate regions.

[0070] For example, if the difference between the confidence levels of all risk areas is small, when the maximum confidence level of a risk area in any output of the leak identification model is 90%, the risk area corresponding to the 90% confidence level can be used as a candidate area; if the leak identification model outputs 10 results, and the frequency of "pre-hydrogen tank area" as a candidate area is the highest value of 6 times, then "pre-hydrogen tank area" can be determined as the leak area.

[0071] In one embodiment of this application, for details on how to determine the leakage area based on confidence level, please refer to [link to relevant documentation]. Figure 5 and Figure 6 The corresponding detailed explanation.

[0072] S25, if the hydrogen concentration data in the leak area is greater than a preset concentration threshold, execute the target control strategy corresponding to the leak area.

[0073] In one embodiment of this application, the identification results of the leak area can be used in conjunction with hydrogen concentration level information to implement a graded and regional active control strategy.

[0074] In one embodiment of this application, the method further includes: when the hydrogen concentration data in the leak area is less than or equal to the concentration threshold, controlling the vehicle to output a preset alarm message; the alarm message includes any one or more combinations of visual information, sound information, and text information. Specifically, if the hydrogen concentration collected in real time by the sensor in any leak area exceeds the preset concentration threshold, but the volume fraction of the hydrogen concentration does not exceed 1%, then the vehicle is determined to have a low-level hydrogen leak or a suspected hydrogen leak. The electronic device can trigger the instrument panel alarm icon and text prompts, and send a reminder message to the vehicle owner through the vehicle communication system; it can also record fault codes for subsequent service and traceability.

[0075] If the volume fraction of hydrogen concentration collected in real time by the sensors in any leak area exceeds 1%, it is determined that an active control strategy needs to be implemented, and the electronic equipment can immediately enter the active control decision-making process.

[0076] In one embodiment of this application, the electronic device receives information related to the leak area from the leak identification model in real time, such as "a certain hydrogen storage cylinder valve area," "pressure reducing valve area," or "pipe connection area." It then queries a pre-defined zone control strategy table for the corresponding control logic. This control strategy table can set different control combinations for different leak areas and different concentration levels (e.g., slightly exceeding 1% and significantly exceeding 1%).

[0077] In one embodiment of this application, different leakage areas correspond to differentiated control strategies.

[0078] For example, each leakage area can correspond to a pre-set combination of control actions. When the leakage area is the front cylinder valve area, the control strategy may include: closing the front cylinder valve while keeping the other cylinder valves open; when the leakage area is the rear cylinder valve area, the control strategy may include: closing the rear cylinder valve while keeping the other cylinder valves open; when the leakage area is the pressure reducing valve area, the control strategy may include: closing the main hydrogen supply valve, shutting down the fuel cell, and switching the vehicle to pure electric mode.

[0079] Specifically, when the leak detection model indicates that the hydrogen leak originates from a specific hydrogen storage cylinder valve area, the electronic equipment controls the corresponding cylinder valve to close. Other hydrogen cylinders not identified as having leaked remain open, continuing to supply hydrogen to the vehicle's fuel cell system. The vehicle's instrument panel continuously displays alarm information. This ensures the vehicle can continue driving at a certain power level and leave the current area, improving the vehicle's availability under hydrogen leak conditions.

[0080] Specifically, when the leak detection model indicates that a leak has occurred in areas such as the pressure relief valve area, pipe connection area, or front fuel cell area, the electronic equipment can send a command to cut off the main hydrogen supply path, close the main pipeline valve, ensure that the fuel cell system stops receiving hydrogen, and control the vehicle to switch to a pure electric operation mode using only the power battery, provided the remaining power battery charge is available. If the remaining power battery charge is available, the vehicle will be controlled to travel to a safe area with limited power.

[0081] In one embodiment of this application, the execution conditions of the control strategy correspond to different priorities. When multiple control strategies conflict, the most conservative action can be executed according to the principle of safety priority. For example, when the leakage area includes both the front cylinder valve area and the pressure reducing valve area, since the control strategy corresponding to the pressure reducing valve area is the safer "close the main hydrogen supply valve, shut down the fuel cell, and switch the vehicle to pure electric mode", the control strategy corresponding to the pressure reducing valve area can be executed first.

[0082] In one embodiment of this application, after the electronic device sends a control command to any actuator such as a bottle valve or main valve, it also monitors the signal feedback information of the open / closed position in real time and determines whether the control strategy has been successfully executed based on the feedback information. If no feedback information is received after a preset time, it indicates that the control strategy has failed, and a higher-level alarm and backup control strategy can be triggered. For example, the backup control strategy could be to directly close all bottle valves.

[0083] In one embodiment of this application, after implementing the control strategy corresponding to the leak area, preset ventilation and additional safety measures can also be implemented. For example, when the hydrogen concentration volume fraction in the leak area is higher than 1%, the vehicle can be controlled to start the forced ventilation function; for enclosed spaces in the front compartment or lower body, an automatic hatch / underbody cover mechanism can also be provided to accelerate the diffusion of leaked gas.

[0084] In one embodiment of this application, the method further includes: after executing the target control strategy corresponding to the leak area, if the hydrogen concentration in the leak area shows a decreasing trend and the hydrogen concentration is less than a safety threshold, controlling the vehicle to output reset request information.

[0085] Specifically, after implementing the active control strategy, the hydrogen concentration change can be continuously monitored. Only when the hydrogen concentration recovers to a safe range within a certain period of time and meets the conditions for maintenance confirmation or manual reset, the electronic equipment sends a recovery command to the on-board equipment in the leak area (e.g., the pressure relief valve in the front hydrogen tank area), indicating that partial or full restoration of hydrogen supply is allowed. This avoids frequent system switching due to accidental triggering or short-term fluctuations, thereby improving stability and safety.

[0086] In one embodiment of this application, a tiered alarm mechanism and threshold conditions are used to issue an early warning for hydrogen leakage events in the vehicle. Specifically, when a sensor detects a hydrogen concentration value greater than a baseline concentration but not exceeding 1%, it is determined to be a warning-level alarm condition. The electronic device activates the instrument panel warning light and displays a text prompt, advising the user to check; at the same time, the event is recorded for tracking.

[0087] As can be seen from the above technical solutions, the embodiments of this application are successful. A complete closed-loop safety method is achieved by performing feature identification on the time series of hydrogen concentrations at multiple points, realizing leak area-level localization, and executing differentiated active control based on different leak locations. This improves the vehicle's early identification capability, positioning accuracy, and active safety control level for hydrogen leaks. Specifically, multiple hydrogen concentration sensors installed in the vehicle monitor hydrogen concentration data in multiple hydrogen-related areas in real time, and identify the hydrogen leak area based on the sequence characteristics of concentration changes. This enables the identification of small, low-flow steady-state leaks. Compared to a single concentration over-limit alarm method, this application can detect potential leaks in the early stages of hydrogen leaks, preventing the leak from spreading. The specific area where the hydrogen leak occurred is determined based on a pre-trained leak identification model, making the control action localized and precise. Combining the area identification results with the corresponding active control strategy reduces the risk of misoperation due to unclear hydrogen leak location judgment, achieving leak area-level localization control and enhancing safety and response accuracy. Different control strategies are set for different leakage areas, and different execution priorities are set for different levels of leakage events. This improves vehicle safety and avoids a one-size-fits-all power interruption, so that the vehicle remains available in the event of a failure.

[0088] like Figure 3 The diagram shown is a flowchart of a method for determining feature data corresponding to each hydrogen-related region according to an embodiment of this application. The order of steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements. The method for determining feature data corresponding to each hydrogen-related region provided in this embodiment includes the following steps.

[0089] S30, based on the target sequence of each hydrogen-related region, determine the first feature data of each hydrogen-related region; the first feature data includes the hydrogen concentration rise rate, the hydrogen concentration rise time constant, the hydrogen concentration peak value, and the hydrogen concentration integral.

[0090] In one embodiment of this application, first feature data corresponding to each hydrogen-related region can be determined based on a target sequence for each hydrogen-related region. The first feature data includes the hydrogen concentration rise rate, the hydrogen concentration rise time constant, the hydrogen concentration peak value, and the hydrogen concentration integral. Specifically, a target sequence with a time range of 5 to 20 seconds can be extracted from the hydrogen concentration sequence collected by each sensor, and the hydrogen concentration rise rate, hydrogen concentration rise time constant, hydrogen concentration peak value, and hydrogen concentration integral corresponding to the hydrogen-related region to which the sensor belongs can be determined based on this target sequence.

[0091] S31, based on the target sequences of any two hydrogen-related regions, determine the second feature data of the arbitrary two hydrogen-related regions; the second feature data includes the response delay difference, peak difference, and ratio of the hydrogen concentration of the arbitrary two hydrogen-related regions.

[0092] In one embodiment of this application, second feature data of any two hydrogen-related regions can be determined based on target sequences of any two hydrogen-related regions. The second feature data includes the response delay difference, peak difference, and ratio of hydrogen concentration between the two hydrogen-related regions.

[0093] S32, standardize the first feature data and the second feature data to obtain feature data.

[0094] In one embodiment of this application, in order to improve the accuracy of subsequent prediction of the leakage area based on the first feature and the second feature, the first feature data and the second feature data can be standardized to obtain feature data, thereby eliminating the dimensional difference between the first feature and the second feature and avoiding errors in the output results of the leakage identification model due to excessive dimensional difference.

[0095] like Figure 4 The diagram shown is a flowchart of a method for training a leak detection model according to an embodiment of this application. The order of steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements. The method for training a leak detection model according to an embodiment of this application includes the following steps.

[0096] S40, based on the area information corresponding to the multiple hydrogen-related areas, the test fluid data of the multiple hydrogen-related areas, and the environmental information of the environment in which the vehicle is located, the leakage characteristics of the vehicle are determined; the leakage characteristics are used to indicate the hydrogen leakage mode of the multiple hydrogen-related areas.

[0097] In one embodiment of this application, based on the actual hydrogen supply system layout of the vehicle, different leakage flow rate, leakage direction, ambient wind speed and direction, etc., can be set for different potential leakage areas (e.g., refueling area, front / rear hydrogen cylinder area, pressure reducing valve area, pipe connection area, fuel cell area, etc.) when the vehicle is stationary; hydrogen concentration-time series data of each sensor under different leakage conditions can be continuously collected by hydrogen concentration sensors arranged at different locations of the vehicle.

[0098] In an optional embodiment, flow field simulation technology can be used to simulate extreme operating conditions that are difficult to cover, and the time-concentration data obtained from the simulation and the actual vehicle test data can be used as training data.

[0099] Potential leak location parameters may include: various high-pressure and low-pressure pipe joints; hydrogen storage cylinder valves; pressure reducing valve inlet / outlet; and connections between flexible and rigid pipes.

[0100] The leakage direction parameter can include: vertically upward, vertically downward; horizontally forward, backward, left, and right. In specific tests, the most probable leakage direction can be selected based on the actual component structure and the expected crack and seal failure direction.

[0101] Among them, the leakage flow rate parameter is used to simulate a low-flow steady-state leakage mode that is difficult to perceive, characterized by a long leakage duration and slow accumulation of hydrogen concentration in the space.

[0102] Among them, environmental operating parameters may include: ambient temperature, ambient pressure; wind speed, wind direction (e.g., no wind indoors, slight ventilation, cross wind, etc.). The above parameters affect the diffusion path and accumulation pattern of hydrogen in the vehicle chassis and cabin, and can be covered in the experimental design or supplemented by simulation.

[0103] In one embodiment of this application, the acquired time-concentration signal can be preprocessed. The preprocessing operation may include: removing outliers, noise filtering, aligning the time axis, interpolation and resampling, and normalizing the accuracy differences of hydrogen concentration data and environmental data acquired by different sensors.

[0104] Hydrogen concentration data can also be classified and stored based on tags such as leakage area, leakage flow rate, and environmental conditions, in preparation for subsequent feature extraction and model building.

[0105] In one embodiment of this application, leakage features are extracted from the response characteristics of various sensors for possible hydrogen leakage modes in different hydrogen-related areas. The leakage features may include: concentration rise rate, rise time constant, peak concentration, stable concentration, etc. of a single sensor; response sequence, response time difference, peak occurrence time difference between multiple sensors; statistical features such as integral concentration, average concentration, and maximum gradient within a certain time window; and feature vectors of different sensor combinations.

[0106] Among them, leakage characteristics can be used to describe the behavioral patterns of hydrogen leakage in different hydrogen-related areas.

[0107] S41, based on the leakage characteristics, the predicted confidence level of each hydrogen-related region is determined using a preset initial identification model.

[0108] In one embodiment of this application, the initial identification model can be any model with data processing, data prediction and data classification functions, and this application does not limit it.

[0109] A leakage feature identification model can be constructed based on the above leakage characteristics, hydrogen-related areas (e.g., filling area, front bottle area, rear bottle area, pressure reducing valve area, etc.) and the corresponding leakage probability as output labels.

[0110] S42, based on the difference between the predicted confidence level and the leakage probability of the pre-labeled multiple hydrogen-related areas, update the initial identification model. When the difference meets the preset termination condition, stop updating the initial identification model and obtain a leakage identification model trained to a convergent state.

[0111] In one embodiment of this application, the greater the difference between the predicted confidence level and the leakage probability of multiple pre-labeled hydrogen-related regions, the lower the accuracy of the predicted confidence level predicted by the initial identification model. In this case, the initial identification model can be continuously updated, and the predicted confidence level corresponding to multiple hydrogen-related regions can be output multiple times using the initial identification model. Conversely, the greater the difference between the predicted confidence level and the leakage probability of multiple pre-labeled hydrogen-related regions, the higher the accuracy of the predicted confidence level predicted by the initial identification model. In this case, the higher the similarity between the predicted confidence level and the leakage probability of multiple pre-labeled hydrogen-related regions, the more certain it is that the initial identification model has been trained to a convergent state, thus obtaining a leakage identification model.

[0112] In one embodiment of this application, the training data can be divided into a training set and a validation set. The parameters of the initial model are adjusted based on the training set, and the performance of the leak detection model trained to a convergent state is verified based on the validation set, ensuring that the leak detection model has stable area identification capabilities under various leak conditions corresponding to the vehicle.

[0113] In one embodiment of this application, the parameters of the leakage identification model can be solidified into a form that can be deployed in the vehicle control unit and adapted to the vehicle controller communication interface.

[0114] like Figure 5 The diagram shown is a flowchart of a method for determining a leakage area based on confidence level according to an embodiment of this application. The order of steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements. The method for determining a leakage area based on confidence level provided in this embodiment of the application includes the following steps.

[0115] S50 determines the difference between the confidence levels of any two risk areas.

[0116] S51, if the difference is higher than a preset difference threshold, the risk area corresponding to the higher confidence level is determined as the leakage area.

[0117] In one embodiment of this application, if the difference between the confidence levels of any two risk areas is higher than the difference threshold, it indicates that the probability of a hydrogen leakage event in the risk area corresponding to the higher confidence level is the highest among all risk areas. Therefore, the risk area corresponding to the higher confidence level can be determined as the leakage area.

[0118] For example, if the difference between the confidence levels corresponding to the "front hydrogen tank area" and the "pressure reducing valve area" is higher than the difference threshold, then if the confidence level corresponding to the "front hydrogen tank area" is higher than the confidence level corresponding to the "pressure reducing valve area", then the "front hydrogen tank area" can be determined as a leaking area.

[0119] like Figure 6 The diagram shown is a flowchart of a method for determining a leakage area based on confidence level according to an embodiment of this application. The order of steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements. The method for determining a leakage area based on confidence level provided in this embodiment of the application includes the following steps.

[0120] S60, if the difference between the confidence levels of any two risk areas is less than or equal to the difference threshold, the confidence level of the risk area is output multiple times using the leakage identification model.

[0121] In one embodiment of this application, if the difference between the confidence levels of all risk areas is small, that is, if the difference between the confidence levels of any two risk areas is less than or equal to the difference threshold, the confidence level of the risk area can be output multiple times using the leakage identification model.

[0122] S61, select the maximum confidence level from the confidence level output by the leakage identification model each time, and take the risk area corresponding to the maximum confidence level as the candidate area to obtain multiple candidate areas corresponding to multiple outputs.

[0123] In one embodiment of this application, to improve the accuracy of determining the leak area, the highest confidence level can be selected from the confidence levels output by the leak identification model each time, and the risk area corresponding to the highest confidence level can be used as a candidate area to obtain multiple candidate areas corresponding to multiple outputs. This reduces the error in determining the leak area and improves the fault tolerance in the process of determining the leak area.

[0124] S62, select the risk area with the highest frequency of occurrence from multiple candidate areas as the leakage area.

[0125] In one embodiment of this application, the risk area with the highest frequency of occurrence can be selected as the leakage area from multiple candidate areas.

[0126] For example, if the difference between the confidence levels of all risk areas is small, when the maximum confidence level of a risk area in any output of the leak identification model is 90%, the risk area corresponding to the 90% confidence level can be used as a candidate area; if the leak identification model outputs 10 results, and the frequency of "pre-hydrogen tank area" as a candidate area is the highest value of 6 times, then "pre-hydrogen tank area" can be determined as the leak area.

[0127] Please see Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 100 includes a memory 12 and a processor 13. The memory 12 is used to store computer-readable instructions, and the processor 13 executes the computer-readable instructions stored in the memory to implement a hydrogen leakage control method as described in any of the above embodiments.

[0128] In one embodiment of this application, the electronic device 100 further includes a bus and a computer program stored in the memory 12 and executable on the processor 13, such as a hydrogen leak control program.

[0129] Figure 7 Only an electronic device 100 with memory 12 and processor 13 is shown; those skilled in the art will understand that... Figure 7 The structure shown does not constitute a limitation on the electronic device 100, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0130] Combination Figure 2The memory 12 in the electronic device 100 stores a plurality of computer-readable instructions to implement the hydrogen leakage control method. The processor 13 can execute the plurality of instructions to achieve the following: based on hydrogen concentration data of multiple hydrogen-related areas of the vehicle within a preset period, determine the hydrogen concentration sequence corresponding to each hydrogen-related area; when the hydrogen concentration sequences of the multiple hydrogen-related areas meet preset abnormal conditions, determine the target sequence corresponding to each hydrogen-related area within a preset time range from the hydrogen concentration sequences; based on the target sequence of each hydrogen-related area and the quantitative relationship between the target sequences of any two hydrogen-related areas, determine the feature data corresponding to each hydrogen-related area within the time range; based on the feature data, determine the risk area and the confidence level corresponding to the risk area from the multiple hydrogen-related areas using a preset leakage identification model; wherein, the leakage identification model is trained by the area information corresponding to the multiple hydrogen-related areas, the test fluid data of the multiple hydrogen-related areas, and the environmental information of the environment in which the vehicle is located; based on the confidence level, determine the leakage area from the risk area; when the hydrogen concentration data of the leakage area is greater than a preset concentration threshold, execute the target control strategy corresponding to the leakage area.

[0131] Specifically, the processor 13's implementation method for the above instructions can be found in [reference needed]. Figure 2 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0132] Those skilled in the art will understand that the schematic diagram is merely an example of the electronic device 100 and does not constitute a limitation on the electronic device 100. The electronic device 100 may be a bus-type structure or a star-type structure. The electronic device 100 may also include more or fewer other hardware or software than shown in the diagram, or different component arrangements. For example, the electronic device 100 may also include input / output devices, network access devices, etc.

[0133] It should be noted that electronic device 100 is only an example. Other existing or future electronic products that are suitable for this application should also be included within the scope of protection of this application and are incorporated herein by reference.

[0134] The memory 12 includes at least one type of readable storage medium, which can be non-volatile or volatile. The readable storage medium includes flash memory, portable hard drives, multimedia cards, card-type memory (e.g., SD or DX memory), magnetic storage, magnetic disks, optical disks, etc. In some embodiments, the memory 12 can be an internal storage unit of the electronic device 100, such as the portable hard drive of the electronic device 100. In other embodiments, the memory 12 can also be an external storage device of the electronic device 100, such as a plug-in portable hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 100. The memory 12 can be used not only to store application software and various types of data installed on the electronic device 100, such as the code of a hydrogen leak control program, but also to temporarily store data that has been output or will be output.

[0135] In some embodiments, the processor 13 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits packaged with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 13 is the control unit of the electronic device 100, connecting to various components of the electronic device 100 via various interfaces and lines. It executes programs or modules stored in the memory 12 (e.g., executing hydrogen leak control programs) and calls data stored in the memory 12 to perform various functions of the electronic device 100 and process data.

[0136] The processor 13 executes the operating system of the electronic device 100 and various installed applications. The processor 13 executes the applications to implement the steps in the various hydrogen leakage control method embodiments described above, for example... Figure 2 The steps are shown.

[0137] For example, the computer program may be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 13 to complete this application. The one or more modules / units may be a series of computer-readable instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device 100.

[0138] The integrated unit implemented as a software functional module described above can be stored in a computer-readable storage medium. This software functional module, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, computer equipment, or network device, etc.) or processor to execute portions of the hydrogen leakage control method described in the various embodiments of this application.

[0139] If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware devices. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above.

[0140] The computer program includes computer program code, which may be in the form of source code, foreground object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory, and other memory.

[0141] Furthermore, the computer-readable storage medium may primarily include a stored program area and a stored data area, wherein the stored program area may store the operating system, an application program required for at least one function, etc.; and the stored data area may store data created based on the use of blockchain nodes, etc.

[0142] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, in... Figure 7 The symbol is represented by only one arrow, but this does not indicate that there is only one bus or one type of bus. The bus is configured to enable communication between the memory 12 and at least one processor 13, etc.

[0143] This application also provides a computer-readable storage medium (not shown), which stores computer-readable instructions that are executed by a processor in an electronic device to implement the hydrogen leakage control method described in any of the above embodiments.

[0144] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. The modules described as separate components may or may not be physically separate, and the components shown as modules 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.

[0145] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0146] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices described in the specification may also be implemented by a single unit or device through software or hardware. Terms such as "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0147] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.

Claims

1. A method for controlling hydrogen leakage, characterized in that, The method includes: Based on hydrogen concentration data from multiple hydrogen-related areas of the vehicle within a preset period, a hydrogen concentration sequence corresponding to each hydrogen-related area is determined. When the hydrogen concentration sequences of the multiple hydrogen-related regions meet preset abnormal conditions, a target sequence corresponding to each hydrogen-related region within a preset time range is determined from the hydrogen concentration sequences. Based on the target sequence of each hydrogen-related region and the quantitative relationship between the target sequences of any two hydrogen-related regions, the characteristic data corresponding to each hydrogen-related region within the time range are determined. Based on the feature data, a preset leak identification model is used to determine risk areas and the corresponding confidence levels of the risk areas from the multiple hydrogen-related areas; wherein, the leak identification model is trained by the area information corresponding to the multiple hydrogen-related areas, the test fluid data of the multiple hydrogen-related areas, and the environmental information of the environment in which the vehicle is located; Based on the confidence level, the leakage area is determined from the risk area; If the hydrogen concentration in the leak area exceeds a preset concentration threshold, the target control strategy corresponding to the leak area is executed.

2. The hydrogen leakage control method according to claim 1, characterized in that, The abnormal condition includes any one or more of the following combinations: The hydrogen concentration sequence of any hydrogen-related region indicates that the hydrogen concentration of the hydrogen-related region has an upward trend within the preset period; The hydrogen concentration sequence of any hydrogen-related region indicates that the change in hydrogen concentration is greater than a preset gradient threshold. The maximum value of the hydrogen concentration indicated by the hydrogen concentration sequence corresponding to the multiple hydrogen-related regions is greater than the preset base concentration.

3. The hydrogen leakage control method according to claim 1, characterized in that, The determination of feature data corresponding to each hydrogen-related region within the time range, based on the target sequence of each hydrogen-related region and the quantitative relationship between target sequences of any two hydrogen-related regions, includes: Based on the target sequence of each hydrogen-related region, the first characteristic data of each hydrogen-related region is determined; the first characteristic data includes the hydrogen concentration rise rate, the hydrogen concentration rise time constant, the hydrogen concentration peak value, and the hydrogen concentration integral. Based on the target sequences of any two hydrogen-related regions, determine the second feature data of the two hydrogen-related regions; the second feature data includes the response delay difference, peak difference, and ratio of hydrogen concentration in the two hydrogen-related regions. The first feature data and the second feature data are standardized to obtain feature data.

4. The hydrogen leakage control method according to claim 1, characterized in that, The step of determining the leakage area from the risk area based on the confidence level includes: Determine the difference between the confidence levels of any two risk regions; If the difference is higher than a preset difference threshold, the risk area corresponding to the higher confidence level is identified as the leakage area.

5. The hydrogen leakage control method according to claim 4, characterized in that, The step of determining the leakage area from the risk area based on the confidence level includes: If the difference between the confidence levels of any two risk regions is less than or equal to the difference threshold, the confidence level of the risk region is output multiple times using the leakage identification model. The maximum confidence level is selected from the confidence level of each output of the leakage identification model, and the risk area corresponding to the maximum confidence level is used as the candidate area to obtain multiple candidate areas corresponding to multiple outputs. The risk area that appears most frequently among multiple candidate areas is selected as the leakage area.

6. The hydrogen leakage control method according to claim 1, characterized in that, The method further includes: If the hydrogen concentration data in the leak area is less than or equal to the concentration threshold, the vehicle is controlled to output a preset alarm message; the alarm message includes any one or more combinations of visual information, sound information and text information.

7. The hydrogen leakage control method according to claim 1, characterized in that, The method further includes: After executing the target control strategy corresponding to the leak area, if the hydrogen concentration in the leak area shows a decreasing trend and the hydrogen concentration is less than the safety threshold, the vehicle is controlled to output a reset request information.

8. The hydrogen leakage control method according to claim 1, characterized in that, The method further includes: training the leakage detection model, including: Based on the regional information corresponding to the multiple hydrogen-related areas, the test fluid data of the multiple hydrogen-related areas, and the environmental information of the vehicle's environment, the leakage characteristics of the vehicle are determined; the leakage characteristics are used to indicate the hydrogen leakage pattern of the multiple hydrogen-related areas. Based on the leakage characteristics, the predicted confidence level of each hydrogen-related region is determined using a preset initial identification model; Based on the difference between the predicted confidence level and the leakage probability of the pre-labeled multiple hydrogen-related areas, the initial identification model is updated. When the difference meets the preset termination condition, the update of the initial identification model is stopped, and a leakage identification model trained to a convergent state is obtained.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory, the processor being configured to execute a computer program stored in the memory to implement the hydrogen leakage control method as described in any one of claims 1 to 8.

10. A vehicle, characterized in that, The vehicle includes the electronic equipment as described in claim 9.

Images