A hydrogen leakage detection and positioning method and system for a fuel cell vehicle-mounted hydrogen system

Abstract

The present application relates to the technical field of vehicle-mounted hydrogen system safety, and discloses a hydrogen leakage detection and positioning method and system for a fuel cell vehicle-mounted hydrogen system, which comprises establishing a preset candidate leakage source set, collecting concentration data of each hydrogen-sensitive sensor and wind field data of a wind speed and direction acquisition unit, forming a measured response vector at the same sampling time, calculating a predicted response vector of the candidate leakage source at each hydrogen-sensitive sensor, performing matching operation on the predicted response vector and the measured response vector, screening out a target candidate leakage source with a matching degree satisfying a preset condition, determining a target leakage position based on stability or convergence conditions of cumulative results, reading hydrogen-sensitive coating state information arranged at the target leakage position, and obtaining a final leakage position and corresponding alarm information. The present application can guide operation and maintenance personnel to quickly locate and handle the leakage point by accurately identifying the leakage source and generating alarm information, thereby reducing manual investigation time and operation and maintenance cost.

Description

Technical Field

[0001] This invention relates to the field of vehicle-mounted hydrogen system safety technology, and in particular to a method and system for detecting and locating hydrogen leaks in a fuel cell vehicle-mounted hydrogen system. Background Technology

[0002] A fuel cell vehicle's on-board hydrogen system typically includes a hydrogen storage tank, valve body, pressure regulator, hydrogen supply pipeline, pipeline joints, sealing parts, and related connection structures. During vehicle operation, these components may leak hydrogen under conditions of vibration, temperature change, pressure fluctuation, assembly deviation, or long-term service.

[0003] In existing technologies, multiple hydrogen sensors are typically used to detect the hydrogen concentration around the onboard hydrogen system. An alarm is triggered when the detected concentration reaches a preset threshold. Some solutions further incorporate wind speed and direction information to correct the sensor readings and estimate the leak location. Other solutions apply hydrogen-sensitive coatings to pipes, valves, and cylinders, forming a hydrogen-sensitive coating. Technicians manually check for color changes in these coatings. However, in fuel cell vehicle hydrogen systems, potential leak locations are not continuously distributed throughout the space but are typically concentrated at the hydrogen storage cylinder inlet, valve connections, pressure reducer interfaces, and pipe joints. For finite structural parts such as sealing parts and pipeline bends, if the coordinates of the leak point are directly calculated in the open space based solely on the concentration values ​​of each sensor at a certain moment, it is easily affected by factors such as local wind field disturbances, differences in sensor installation positions, structural obstruction, differences in installation height, and spatial proximity of adjacent components. This can lead to discrepancies between the location results and the actual leak location. In addition, most existing hydrogen-sensitive coatings are used as a means of manual verification after location, and their status information is usually not involved in the further screening process within the location model. Therefore, when there are multiple potential leak locations in the vehicle hydrogen system, it is difficult to reliably determine the final leak location by relying solely on a single detection result or manual inspection after location.

[0004] Therefore, there is an urgent need for a method and system for detecting and locating hydrogen leaks in fuel cell vehicle hydrogen systems. Summary of the Invention

[0005] The purpose of this invention is to overcome one or more of the above-mentioned existing technical problems and provide a method and system for detecting and locating hydrogen leaks in a fuel cell vehicle hydrogen system.

[0006] To achieve the above objectives, the present invention provides a method for detecting and locating hydrogen leaks in a fuel cell vehicle on-board hydrogen system, comprising:

[0007] Establish a set of pre-set candidate leakage sources at the hydrogen storage cylinder inlet, valve body connection, pressure reducer interface, pipeline joint, sealing part and pipeline bend of the vehicle hydrogen system and record the spatial coordinates of each candidate leakage source.

[0008] Multiple hydrogen sensors and at least one wind speed and direction acquisition unit are deployed around the vehicle hydrogen system to collect concentration data from each hydrogen sensor and wind field data from the wind speed and direction acquisition unit, forming a measured response vector at the same sampling time.

[0009] For each candidate leak source, the predicted response vector of the candidate leak source at each hydrogen sensor is calculated based on the relative positional relationship between the candidate leak source and each hydrogen sensor, the distance parameter, and the wind field data at the corresponding sampling time.

[0010] The predicted response vector is matched with the measured response vector to obtain the matching degree of each candidate leakage source, and the target candidate leakage source that meets the preset conditions is selected.

[0011] Over multiple consecutive sampling periods, the matching degree of each target candidate leakage source is accumulated over time, and the target leakage location is determined based on the stability or convergence condition of the accumulated results.

[0012] Read the status information of the hydrogen-sensitive coating set at the target leak location, and confirm or re-filter the target leak location based on the status information of the hydrogen-sensitive coating to obtain the final leak location and corresponding alarm information.

[0013] According to one aspect of the present invention, a preset set of candidate leak sources is established based on the actual structure of the vehicle-mounted hydrogen system. Each candidate leak source corresponds to a structured candidate node. The structured candidate node includes at least a node number, component type, spatial coordinates, and connection relationship. The component type includes at least a hydrogen storage cylinder inlet, a valve body connection, a pressure reducer interface, a straight pipe joint, a bent pipe joint, and a sealing part. The connection relationship is used to indicate the communication relationship between each candidate leak source and adjacent pipelines or components, so that the leak location is limited to the structural parts of the vehicle-mounted hydrogen system where a leak may actually occur.

[0014] According to one aspect of the present invention, the measured response vector is composed of the concentration data corresponding to each hydrogen sensor at the same sampling time. The concentration data includes data directly acquired by the hydrogen sensor with analog output and data obtained by the transmitter with pulse width modulation signal after signal conversion.

[0015] Signal conversion is achieved using an RC filter circuit or a timer input capture method. Before forming the measured response vector, the data from each hydrogen sensor and the wind field are time-synchronized so that the concentration data and wind field data participating in the matching operation correspond to the same calculation cycle.

[0016] According to one aspect of the invention, the relative position vectors of the candidate leakage source pointing to each hydrogen sensor are calculated;

[0017] The wind direction correction coefficient is determined based on the angular relationship between the relative position vector and the wind speed direction;

[0018] The distance attenuation coefficient is determined based on the distance between the candidate leakage source and each hydrogen sensor;

[0019] The height correction factor and the shading correction factor are determined by combining the installation height difference and the structural shading relationship. Based on the wind direction correction factor, distance attenuation factor, height correction factor and shading correction factor, the predicted response vector corresponding to each candidate leakage source is calculated.

[0020] According to one aspect of the present invention, the predicted response vector and the measured response vector of each candidate leakage source are subjected to difference calculation, normalization calculation or correlation calculation to obtain the matching degree of each candidate leakage source.

[0021] The leak sources are sorted from high to low according to their matching degree, and the candidate leak sources with a matching degree higher than a preset threshold or ranked in the top K are identified as target candidate leak sources. The preset threshold and K value are determined based on laboratory calibration data, vehicle layout calibration data or historical verification data.

[0022] According to one aspect of the present invention, the matching degree sequence of each target candidate leakage source is calculated in a series of consecutive sampling periods, and a sliding time window of length N is constructed.

[0023] Within the sliding time window, the matching degree of each target candidate leakage source is weighted and accumulated according to the concentration peak, wind field stability and the number of effective sensors to obtain the time-series cumulative value of each target candidate leakage source;

[0024] When the cumulative time value of the same target candidate leak source meets the preset conditions in multiple consecutive sliding time windows, and the sorting position remains unchanged or does not change within the preset range, the target candidate leak source is determined as the target leak location.

[0025] According to one aspect of the present invention, when the hydrogen-sensitive coating status information corresponds to the target leakage location, the target leakage location is determined as the final leakage location; when the hydrogen-sensitive coating status information does not correspond to the target leakage location, the matching weight of the target leakage location is reduced, and the matching operation and time-series accumulation are re-executed for adjacent candidate leakage sources that have a connection relationship with it, and the final leakage location is re-determined.

[0026] To achieve the above objectives, the present invention provides a hydrogen leak detection and location system for a fuel cell vehicle on-board hydrogen system, comprising:

[0027] Candidate Leakage Source Set Establishment Module: Establishes a preset set of candidate leakage sources at the hydrogen storage cylinder inlet, valve body connection, pressure reducer interface, pipeline joint, sealing part and pipeline bend of the on-board hydrogen system and records the spatial coordinates of each candidate leakage source.

[0028] Measured response vector module: Multiple hydrogen sensors and at least one wind speed and direction acquisition unit are deployed around the vehicle hydrogen system to collect concentration data from each hydrogen sensor and wind field data from the wind speed and direction acquisition unit to form a measured response vector at the same sampling time.

[0029] Predicted response vector acquisition module: For each candidate leak source, based on the relative positional relationship between the candidate leak source and each hydrogen sensor, the distance parameter, and the wind field data at the corresponding sampling time, calculate the predicted response vector of the candidate leak source at each hydrogen sensor.

[0030] Target candidate leakage source acquisition module: performs matching operation between the predicted response vector and the measured response vector to obtain the matching degree of each candidate leakage source, and filters out the target candidate leakage sources whose matching degree meets the preset conditions;

[0031] Target Leakage Location Determination Module: Over multiple consecutive sampling periods, the matching degree of each candidate leak source is accumulated over time, and the target leak location is determined based on the stability or convergence condition of the accumulated results.

[0032] Final Leakage Location Acquisition Module: Reads the status information of the hydrogen-sensitive coating set at the target leakage location, and confirms or re-filters the target leakage location based on the status information of the hydrogen-sensitive coating to obtain the final leakage location and corresponding alarm information.

[0033] To achieve the above objectives, the present invention provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the above-described method for detecting and locating hydrogen leaks in a fuel cell vehicle hydrogen system.

[0034] To achieve the above objectives, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described method for detecting and locating hydrogen leaks in a fuel cell vehicle hydrogen system.

[0035] Based on this, the beneficial effects of the present invention are as follows: by establishing a preset set of candidate leakage sources and recording the spatial coordinates of each candidate leakage source, and combining the measured data of multiple sensors with the predicted response vector corrected based on multiple factors such as wind field, distance, and occlusion relationship, the specific location of the leakage can be accurately located in complex vehicle layout and dynamic wind field environment, avoiding the limitation of traditional methods that can only alarm but cannot locate.

[0036] The system introduces a wind speed and direction acquisition unit and comprehensively considers wind direction correction coefficient, distance attenuation coefficient, height correction coefficient and shading correction coefficient in the prediction model. It can effectively suppress the influence of environmental wind field changes, structural shading and sensor installation height differences on concentration distribution and improve the adaptability of the detection algorithm under real working conditions.

[0037] After the algorithm locates the target leak location, it further reads the state information of the hydrogen-sensitive coating set at that location for physical layer confirmation. If the two are consistent, the leak location is finally confirmed. If they are inconsistent, a re-screening mechanism is triggered to reduce the weight of mismatches and recalculate adjacent candidate sources, forming a dual verification mechanism, which greatly improves the accuracy and reliability of the detection results.

[0038] By accurately identifying the source of the leak and generating alarm information, it can guide maintenance personnel to quickly locate and handle the leak point, reduce manual inspection time, lower maintenance costs, and effectively prevent hydrogen accumulation from causing safety accidents, thus significantly improving the overall safety and reliability of fuel cell vehicles. Attached Figure Description

[0039] Figure 1 This is a flowchart illustrating a method for detecting and locating hydrogen leaks in a fuel cell vehicle on-board hydrogen system, according to an exemplary embodiment.

[0040] Figure 2 This is a flowchart illustrating a hydrogen leak detection and location system for a fuel cell vehicle-mounted hydrogen system according to an exemplary embodiment. Detailed Implementation

[0041] The invention will now be discussed with reference to exemplary embodiments. It should be understood that the described embodiments are merely intended to enable those skilled in the art to better understand and thus implement the invention, and are not intended to imply any limitation on the scope of the invention.

[0042] As used herein, the term “comprising” and its variations are to be interpreted as open-ended terms meaning “including but not limited to”. The term “based on” is to be interpreted as “at least partially based on”, and the terms “one embodiment” and “an embodiment” are to be interpreted as “at least one embodiment”.

[0043] According to one embodiment of the present invention, Figure 1 This is a flowchart illustrating a method for detecting and locating hydrogen leaks in a fuel cell vehicle on-board hydrogen system, according to an exemplary embodiment. Figure 1 As shown, to achieve the above objectives, the present invention provides a method for detecting and locating hydrogen leaks in a fuel cell vehicle on-board hydrogen system, comprising:

[0044] Establish a set of pre-set candidate leakage sources at the hydrogen storage cylinder inlet, valve body connection, pressure reducer interface, pipeline joint, sealing part and pipeline bend of the vehicle hydrogen system and record the spatial coordinates of each candidate leakage source.

[0045] Multiple hydrogen sensors and at least one wind speed and direction acquisition unit are deployed around the vehicle hydrogen system to collect concentration data from each hydrogen sensor and wind field data from the wind speed and direction acquisition unit, forming a measured response vector at the same sampling time.

[0046] For each candidate leak source, the predicted response vector of the candidate leak source at each hydrogen sensor is calculated based on the relative positional relationship between the candidate leak source and each hydrogen sensor, the distance parameter, and the wind field data at the corresponding sampling time.

[0047] The predicted response vector is matched with the measured response vector to obtain the matching degree of each candidate leakage source, and the target candidate leakage source that meets the preset conditions is selected.

[0048] Over multiple consecutive sampling periods, the matching degree of each target candidate leakage source is accumulated over time, and the target leakage location is determined based on the stability or convergence condition of the accumulated results.

[0049] Read the status information of the hydrogen-sensitive coating set at the target leak location, and confirm or re-filter the target leak location based on the status information of the hydrogen-sensitive coating to obtain the final leak location and corresponding alarm information.

[0050] According to one embodiment of the present invention, a preset set of candidate leak sources is established based on the actual structure of the vehicle-mounted hydrogen system. Each candidate leak source corresponds to a structured candidate node. The structured candidate node includes at least a node number, component type, spatial coordinates, and connection relationship. The component type includes at least a hydrogen storage cylinder inlet, a valve body connection, a pressure reducer interface, a straight pipe joint, a bent pipe joint, and a sealing part. The connection relationship is used to indicate the communication relationship between each candidate leak source and adjacent pipelines or components, so that the leak location is limited to the structural parts of the vehicle-mounted hydrogen system where leaks may actually occur.

[0051] According to one embodiment of the present invention, the measured response vector is composed of the concentration data corresponding to each hydrogen sensor at the same sampling time. The concentration data includes the data directly acquired by the hydrogen sensor with analog output and the data obtained by the transmitter with pulse width modulation signal after signal conversion.

[0052] Signal conversion is achieved using an RC filter circuit or a timer input capture method. Before forming the measured response vector, the data from each hydrogen sensor and the wind field are time-synchronized so that the concentration data and wind field data participating in the matching operation correspond to the same calculation cycle.

[0053] According to one embodiment of the present invention, the relative position vectors of the candidate leakage source pointing to each hydrogen sensor are calculated;

[0054] The wind direction correction coefficient is determined based on the angular relationship between the relative position vector and the wind speed direction;

[0055] The distance attenuation coefficient is determined based on the distance between the candidate leakage source and each hydrogen sensor;

[0056] The height correction factor and the shading correction factor are determined by combining the installation height difference and the structural shading relationship. Based on the wind direction correction factor, distance attenuation factor, height correction factor and shading correction factor, the predicted response vector corresponding to each candidate leakage source is calculated.

[0057] According to one embodiment of the present invention, the predicted response vector and the measured response vector of each candidate leakage source are subjected to difference calculation, normalization calculation or correlation calculation to obtain the matching degree of each candidate leakage source.

[0058] The leak sources are sorted from high to low according to their matching degree, and the candidate leak sources with a matching degree higher than a preset threshold or ranked in the top K are identified as target candidate leak sources. The preset threshold and K value are determined based on laboratory calibration data, vehicle layout calibration data or historical verification data.

[0059] According to one embodiment of the present invention, the matching degree sequence of each target candidate leakage source is calculated in multiple consecutive sampling periods, and a sliding time window of length N is constructed.

[0060] Within the sliding time window, the matching degree of each target candidate leakage source is weighted and accumulated according to the concentration peak, wind field stability and the number of effective sensors to obtain the time-series cumulative value of each target candidate leakage source;

[0061] When the cumulative time value of the same target candidate leak source meets the preset conditions in multiple consecutive sliding time windows, and the sorting position remains unchanged or does not change within the preset range, the target candidate leak source is determined as the target leak location.

[0062] According to one embodiment of the present invention, when the hydrogen-sensitive coating status information corresponds to the target leakage location, the target leakage location is determined as the final leakage location; when the hydrogen-sensitive coating status information does not correspond to the target leakage location, the matching weight of the target leakage location is reduced, and the matching operation and time-series accumulation are re-executed for adjacent candidate leakage sources that have a connection relationship with it, and the final leakage location is re-determined.

[0063] According to one embodiment of the present invention, a preset set of candidate leak sources is established based on the actual structure of the on-board hydrogen system. Each candidate leak source corresponds to a structured candidate node. The component types include at least a hydrogen storage cylinder inlet, a valve body connection, a pressure reducer interface, a straight pipe connector, a bend connector, and a sealing part. Spatial coordinates can be described using a two-dimensional or three-dimensional coordinate system. Connection relationships are used to characterize the structural connectivity between each candidate leak source and adjacent pipelines or components. Using this method, subsequent matching calculations are limited to structural locations in the on-board hydrogen system where leaks may actually occur, rather than arbitrary points in space. For two adjacent candidate leak sources, such as the pressure reducer outlet connector and its connected sealing part, they can be processed sequentially according to their connection relationships during subsequent re-screening.

[0064] According to one embodiment of the present invention, the data acquisition of each transmitter includes hydrogen sensor data acquisition and anemometer data acquisition. The sensor deployment includes several hydrogen sensors and several anemometers with fixed frames. If a transmitter with a PWM output signal is used, it is converted into a stable analog voltage that can be recognized by an ADC using an RC circuit or a microcontroller timer input capture function. Based on this, for hydrogen sensors with analog output, their output signal can be directly entered into the analog-to-digital conversion module. For transmitters with PWM output, the PWM signal is first converted into a recognizable analog or digital signal through an RC filter circuit or a microcontroller timer input capture method, and then the concentration data is obtained. The wind speed and wind direction data output by the anemometers are synchronously received by the monitoring and identification unit. Before forming the measured response vector, the monitoring and identification unit performs time synchronization, zero-point calibration, drift compensation, outlier removal, and noise filtering on the concentration data and wind speed and wind direction data of each hydrogen sensor. The processed data of each channel form a measured response vector at the same timestamp, which is used for subsequent matching calculations.

[0065] According to one embodiment of the present invention, the concentration value of each sensor is weighted. The physical location of the hydrogen sensor is a coordinate system. The coordinates of the leak point are calculated by weighted average, a suitable centroid is selected, and a rectangular coordinate system is established. Let the physical coordinates of the sensor deployment location be... When the wind speed is less than 0.5 m / s, it is considered a windless environment, and the initial leak point coordinates are directly used. Without concentration correction, when the wind speed is not less than 0.5 m / s, the collected wind direction angle is converted to radians.

[0066] ;

[0067] ;

[0068] in, This indicates that the hydrogen concentration detected by the i-th sensor is in ppm.

[0069] Represents the coordinates of the i-th sensor;

[0070] Collect the wind direction angle Convert to radians and calculate the wind speed components in the x and y directions.

[0071] ;

[0072] ;

[0073] in, Indicates wind speed;

[0074] For each sensor Calculate its position vector relative to the leak point. And its relative position with respect to the wind direction is determined by the dot product.

[0075] ;

[0076] ;

[0077] ;

[0078] ;

[0079] in, Indicates the first The degree of matching between wind direction and sensor location;

[0080] Indicates the first The straight-line distance from each sensor to the initial leak point;

[0081] This indicates the total wind speed;

[0082] Indicates the first Correction ratio coefficient for each sensor.

[0083] ;

[0084] in, This indicates the concentration after wind speed correction;

[0085] This represents the wind speed correction factor, obtained through laboratory calibration.

[0086] Use the corrected concentration The weighted centroid was recalculated to obtain the final coordinates of the leak point. . 、

[0087] According to one embodiment of the present invention, during the production and assembly process, a hydrogen-sensitive coating is applied to the outer surface of pipelines, valve bodies, bottles, joints, and seals. The hydrogen-sensitive coating is formed by hydrogen-sensitive paint, and technicians can investigate and verify the reported leak points. In this invention, the state of the hydrogen-sensitive coating is also used as a re-screening input to determine the final leak location. After determining the target leak location, the state information of the hydrogen-sensitive coating at the target leak location is read. The state information can be entered by technicians on-site, obtained by color recognition after acquisition by an image acquisition unit, or detected by a color sensor. When the state of the hydrogen-sensitive coating corresponds to the target leak location, the target leak location is determined as the final leak location. When the state of the hydrogen-sensitive coating does not correspond to the target leak location, the matching weight of the target leak location is reduced, and the matching operation and time accumulation are re-executed only for adjacent candidate leak sources connected to it to redetermine the final leak location.

[0088] According to one embodiment of the present invention, once the final leak location is determined, an alarm message is output based on the hydrogen concentration value of the area corresponding to the final leak location. The alarm level includes at least three levels: Level 1 alarm threshold is greater than or equal to 5000 ppm, Level 2 alarm threshold is greater than or equal to 20000 ppm, and Level 3 alarm threshold is greater than or equal to 40000 ppm. When outputting the alarm message, the final leak location number, candidate node coordinates, valid sensor number participating in the matching, matching degree sequence of each sampling period, and current wind field parameters can also be output simultaneously for subsequent maintenance and manual verification.

[0089] According to one embodiment of the present invention, a fuel cell vehicle-mounted hydrogen system includes a hydrogen storage tank, a main valve body, a pressure reducer, two hydrogen supply pipelines, multiple pipeline joints, and several sealing parts. Eight candidate leakage sources are pre-established at the hydrogen storage tank opening, the main valve body connection, the pressure reducer inlet, the pressure reducer outlet, the first pipeline joint, the second pipeline joint, the first sealing part, and the second sealing part, and their spatial coordinates and connection relationships are recorded. Six hydrogen sensors and one anemometer are deployed around the system. During operation, the concentration data collected by the six hydrogen sensors are respectively input into the monitoring and identification unit. For transmitters with PWM signal outputs, the input capture mode is first converted through an RC circuit or a microcontroller timer before reading. The monitoring and identification unit performs time synchronization of the concentration data and the anemometer data, forming... The measured response vector at the same sampling moment, at which the anemometer detected a wind speed of 0.9 m / s, the monitoring and identification unit first performs a weighted average calculation based on the concentration values ​​of each hydrogen sensor and the physical coordinates to obtain an initial coarse positioning result. Then, based on the wind direction angle decomposition, the wind speed components in the x and y directions are obtained, and the concentration values ​​of each hydrogen sensor are corrected sensor by sensor. Then, the weighted centroid is recalculated based on the corrected concentration to obtain the corrected coarse positioning result. Based on the coarse positioning result, the calculation range of the candidate leakage source set is narrowed. Then, for the candidate leakage sources in the narrowed range, the predicted response vector is calculated based on its relative positional relationship with each hydrogen sensor, distance parameters, wind speed and direction parameters, installation height difference, and structural obstruction relationship, and the predicted response vector is matched with the normalized difference of the measured response vector. The matching results showed that the second pipe joint had the highest matching degree. Over multiple consecutive sampling periods, the matching degree of the second pipe joint was accumulated over time. The results showed that it maintained the highest ranking across multiple sliding time windows, meeting the preset stability condition. Therefore, the second pipe joint was identified as the target leak location. Subsequently, the status information of the hydrogen-sensitive coating at the second pipe joint was read. The identification results showed that the hydrogen-sensitive coating at this location underwent a color change. Therefore, the second pipe joint was confirmed as the final leak location. Since the concentration in the corresponding area reached over 5000 ppm but not 20000 ppm, a Level 1 alarm was output.

[0090] According to one embodiment of the present invention, in a fuel cell vehicle hydrogen system, a preset set of candidate leakage sources includes multiple candidate leakage sources such as the main valve body connection, the pressure reducer inlet connector, the pressure reducer outlet connector, the first sealing part, the second sealing part, and the bend connector. The pressure reducer outlet connector and the second sealing part are structurally adjacent and connected. Eight hydrogen sensors and one anemometer are deployed around the system. During a detection process, each hydrogen sensor and anemometer forms a measured response vector at the same sampling time. The monitoring and identification unit first calculates the predicted response vector for each candidate leakage source and performs correlation calculation with the measured response vector. The initial matching result shows that the matching degree of the pressure reducer outlet connector and the second sealing part is relatively high, with the pressure reducer outlet connector being slightly higher. Therefore, the pressure reducer outlet connector is first identified as the target candidate leakage source. Subsequently, time-series accumulation is performed in multiple consecutive sampling periods, and the pressure reducer outlet connector still maintains a high ranking, thus being identified as the target leakage location. However, when reading the hydrogen-sensitive coating status information, it was found that the hydrogen-sensitive coating at the pressure reducer outlet connector did not change color, while the hydrogen-sensitive coating at the second sealing part, which is connected to it, did change color. Based on this, the monitoring and identification unit reduced the matching weight of the pressure reducer outlet connector and only re-performed the matching calculation and time accumulation for adjacent candidate leak sources connected to it, namely the second sealing part and the bend connector connected to it. After recalculation, the second sealing part obtained the highest time accumulation value in the new sliding time window, and its hydrogen-sensitive coating status corresponded to it. Therefore, the second sealing part was identified as the final leak location. If the concentration in this area reaches 20,000 ppm or higher but less than 40,000 ppm, a level two alarm message is output.

[0091] Furthermore, to achieve the aforementioned objectives, this invention also provides a hydrogen leak detection and location system for a fuel cell vehicle on-board hydrogen system. Figure 2 This is a flowchart illustrating a hydrogen leak detection and location system for a fuel cell vehicle on-board hydrogen system according to an exemplary embodiment, such as... Figure 2 As shown, a hydrogen leak detection and location system for a fuel cell vehicle hydrogen system according to the present invention includes:

[0092] Candidate Leakage Source Set Establishment Module: Establishes a preset set of candidate leakage sources at the hydrogen storage cylinder inlet, valve body connection, pressure reducer interface, pipeline joint, sealing part and pipeline bend of the on-board hydrogen system and records the spatial coordinates of each candidate leakage source.

[0093] Measured response vector module: Multiple hydrogen sensors and at least one wind speed and direction acquisition unit are deployed around the vehicle hydrogen system to collect concentration data from each hydrogen sensor and wind field data from the wind speed and direction acquisition unit to form a measured response vector at the same sampling time.

[0094] Predicted response vector acquisition module: For each candidate leak source, based on the relative positional relationship between the candidate leak source and each hydrogen sensor, the distance parameter, and the wind field data at the corresponding sampling time, calculate the predicted response vector of the candidate leak source at each hydrogen sensor.

[0095] Target candidate leakage source acquisition module: performs matching operation between the predicted response vector and the measured response vector to obtain the matching degree of each candidate leakage source, and filters out the target candidate leakage sources whose matching degree meets the preset conditions;

[0096] Target Leakage Location Determination Module: Over multiple consecutive sampling periods, the matching degree of each candidate leak source is accumulated over time, and the target leak location is determined based on the stability or convergence condition of the accumulated results.

[0097] Final Leakage Location Acquisition Module: Reads the status information of the hydrogen-sensitive coating set at the target leakage location, and confirms or re-filters the target leakage location based on the status information of the hydrogen-sensitive coating to obtain the final leakage location and corresponding alarm information.

[0098] To achieve the above-mentioned objectives, the present invention also provides an electronic device, which includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the above-mentioned method for detecting and locating hydrogen leaks in a fuel cell vehicle hydrogen system.

[0099] To achieve the above-mentioned objectives, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned method for detecting and locating hydrogen leaks in a fuel cell vehicle hydrogen system.

[0100] Those skilled in the art will recognize that the modules and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0101] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described apparatus and equipment can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0102] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0103] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.

[0104] In addition, the functional modules in the embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0105] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the energy-saving signal transmission / reception methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0106] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

[0107] It should be understood that the sequence number of each step in the invention and embodiments of the present invention does not absolutely imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

Claims

1. A method for detecting and locating hydrogen leaks in a fuel cell vehicle on-board hydrogen system, characterized in that, include: Establish a set of pre-set candidate leakage sources at the hydrogen storage cylinder inlet, valve body connection, pressure reducer interface, pipeline joint, sealing part and pipeline bend of the vehicle hydrogen system and record the spatial coordinates of each candidate leakage source. Multiple hydrogen sensors and at least one wind speed and direction acquisition unit are deployed around the vehicle hydrogen system to collect concentration data from each hydrogen sensor and wind field data from the wind speed and direction acquisition unit, forming a measured response vector at the same sampling time. The method for forming the measured response vector at the same sampling time is as follows: the measured response vector is composed of the concentration data corresponding to each hydrogen sensor at the same sampling time. The concentration data includes the data directly collected by the hydrogen sensor with analog output and the data obtained by the transmitter with pulse width modulation signal after signal conversion. Signal conversion is achieved using an RC filter circuit or a timer input capture method. Before forming the measured response vector, the data from each hydrogen sensor and the wind field data are time-synchronized to ensure that the concentration data and wind field data participating in the matching operation correspond to the same calculation cycle. For each candidate leak source, the predicted response vector of the candidate leak source at each hydrogen sensor is calculated based on the relative positional relationship between the candidate leak source and each hydrogen sensor, the distance parameter, and the wind field data at the corresponding sampling time. The method for calculating the predicted response vector of the candidate leakage source at each hydrogen sensor is to calculate the relative position vector of the candidate leakage source pointing to each hydrogen sensor. The wind direction correction coefficient is determined based on the angle relationship between the relative position vector and the wind speed direction; The distance attenuation coefficient is determined based on the distance between the candidate leakage source and each hydrogen sensor; The height correction factor and the shading correction factor are determined by combining the installation height difference and the structural shading relationship. Based on the wind direction correction factor, distance attenuation factor, height correction factor and shading correction factor, the predicted response vector corresponding to each candidate leakage source is calculated. The predicted response vector is matched with the measured response vector to obtain the matching degree of each candidate leakage source, and the target candidate leakage source that meets the preset conditions is selected. Over multiple consecutive sampling periods, the matching degree of each target candidate leakage source is accumulated over time, and the target leakage location is determined based on the stability or convergence condition of the accumulated results. Read the status information of the hydrogen-sensitive coating set at the target leak location, and confirm or re-filter the target leak location based on the status information of the hydrogen-sensitive coating to obtain the final leak location and corresponding alarm information.

2. The method for detecting and locating hydrogen leaks in a fuel cell vehicle on-board hydrogen system as described in claim 1, characterized in that, The set of pre-defined candidate leak sources is established based on the actual structure of the on-board hydrogen system. Each candidate leak source corresponds to a structured candidate node. The structured candidate node includes at least a node number, component type, spatial coordinates, and connection relationship. The component type includes at least a hydrogen storage cylinder inlet, valve body connection, pressure reducer interface, straight pipe joint, bend pipe joint, and sealing part. The connection relationship is used to indicate the connection relationship between each candidate leak source and adjacent pipelines or components, so that the leak location is limited to the structural parts of the on-board hydrogen system that may actually leak.

3. The method for detecting and locating hydrogen leaks in a fuel cell vehicle on-board hydrogen system as described in claim 2, characterized in that, The matching degree of each candidate leakage source is obtained by performing difference calculation, normalization calculation, or correlation calculation on the predicted response vector and the measured response vector of each candidate leakage source. The leak sources are sorted from high to low according to their matching degree, and the candidate leak sources with a matching degree higher than a preset threshold or ranked in the top K are identified as target candidate leak sources. The preset threshold and K value are determined based on laboratory calibration data, vehicle layout calibration data or historical verification data.

4. The method for detecting and locating hydrogen leaks in a fuel cell vehicle on-board hydrogen system as described in claim 3, characterized in that, The matching degree sequence of each target candidate leakage source is calculated in multiple consecutive sampling periods, and a sliding time window of length N is constructed. Within the sliding time window, the matching degree of each target candidate leakage source is weighted and accumulated according to the concentration peak, wind field stability and the number of effective sensors to obtain the time-series cumulative value of each target candidate leakage source; When the cumulative time value of the same target candidate leak source meets the preset conditions in multiple consecutive sliding time windows, and the sorting position remains unchanged or does not change within the preset range, the target candidate leak source is determined as the target leak location.

5. The method for detecting and locating hydrogen leaks in a fuel cell vehicle on-board hydrogen system as described in claim 4, characterized in that, When the hydrogen-sensitive coating status information corresponds to the target leak location, the target leak location is determined as the final leak location. When the hydrogen-sensitive coating status information does not correspond to the target leak location, the matching weight of the target leak location is reduced, and the matching operation and time-series accumulation are re-executed for adjacent candidate leak sources that are connected to it, and the final leak location is re-determined.

6. A hydrogen leak detection and location system for a fuel cell vehicle on-board hydrogen system, used to execute the hydrogen leak detection and location method for a fuel cell vehicle on-board hydrogen system according to any one of claims 1-5, characterized in that, include: Candidate Leakage Source Set Establishment Module: Establishes a preset set of candidate leakage sources at the hydrogen storage cylinder inlet, valve body connection, pressure reducer interface, pipeline joint, sealing part and pipeline bend of the on-board hydrogen system and records the spatial coordinates of each candidate leakage source. Measured response vector module: Multiple hydrogen sensors and at least one wind speed and direction acquisition unit are deployed around the vehicle hydrogen system to collect concentration data from each hydrogen sensor and wind field data from the wind speed and direction acquisition unit to form a measured response vector at the same sampling time. The method for forming the measured response vector at the same sampling time is as follows: the measured response vector is composed of the concentration data corresponding to each hydrogen sensor at the same sampling time. The concentration data includes the data directly collected by the hydrogen sensor with analog output and the data obtained by the transmitter with pulse width modulation signal after signal conversion. Signal conversion is achieved using an RC filter circuit or a timer input capture method. Before forming the measured response vector, the data from each hydrogen sensor and the wind field data are time-synchronized to ensure that the concentration data and wind field data participating in the matching operation correspond to the same calculation cycle. Predicted response vector acquisition module: For each candidate leak source, based on the relative positional relationship between the candidate leak source and each hydrogen sensor, the distance parameter, and the wind field data at the corresponding sampling time, calculate the predicted response vector of the candidate leak source at each hydrogen sensor. The method for calculating the predicted response vector of the candidate leakage source at each hydrogen sensor is to calculate the relative position vector of the candidate leakage source pointing to each hydrogen sensor. The wind direction correction coefficient is determined based on the angle relationship between the relative position vector and the wind speed direction; The distance attenuation coefficient is determined based on the distance between the candidate leakage source and each hydrogen sensor; The height correction factor and the shading correction factor are determined by combining the installation height difference and the structural shading relationship. Based on the wind direction correction factor, distance attenuation factor, height correction factor and shading correction factor, the predicted response vector corresponding to each candidate leakage source is calculated. Target candidate leakage source acquisition module: performs matching operation between the predicted response vector and the measured response vector to obtain the matching degree of each candidate leakage source, and filters out the target candidate leakage sources whose matching degree meets the preset conditions; Target Leakage Location Determination Module: Over multiple consecutive sampling periods, the matching degree of each candidate leak source is accumulated over time, and the target leak location is determined based on the stability or convergence condition of the accumulated results. Final Leakage Location Acquisition Module: Reads the status information of the hydrogen-sensitive coating set at the target leakage location, and confirms or re-filters the target leakage location based on the status information of the hydrogen-sensitive coating to obtain the final leakage location and corresponding alarm information.

7. An electronic device, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When executed by the processor, the computer program implements a method for detecting and locating hydrogen leaks in a fuel cell vehicle hydrogen system as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements a method for detecting and locating hydrogen leaks in a fuel cell vehicle hydrogen system as described in any one of claims 1 to 5.

Images