A method, device, equipment and medium for monitoring hydrogen leakage in fuel cell vehicles

Abstract

This application relates to the field of fuel cell technology and provides a method, apparatus, device, and medium for monitoring hydrogen leakage in fuel cell vehicles. The method includes: acquiring hydrogen leakage change characteristic data at multiple pre-defined locations within the fuel cell vehicle; preprocessing the hydrogen leakage change characteristic data at the multiple locations according to a preset data specification to obtain preprocessed hydrogen leakage change characteristic data at the multiple locations; and transmitting the preprocessed hydrogen leakage change characteristic data at the multiple locations to a pre-trained hydrogen leakage monitoring model to obtain hydrogen leakage monitoring results. This application improves the accuracy of hydrogen leakage monitoring results by using hydrogen leakage change characteristic data from multiple locations and a pre-trained hydrogen leakage monitoring model to determine the hydrogen leakage level and location.

Description

Technical Field

[0001] This application relates to the field of fuel cell technology, specifically to a method, device, equipment, and medium for monitoring hydrogen leakage in fuel cell vehicles. Background Technology

[0002] In response to the global energy shortage and environmental pollution problems, hydrogen fuel cell vehicles are one of the main solutions actively researched by various countries. Hydrogen fuel cell vehicles generally use composite material hydrogen storage cylinders with low density-to-volume ratio and high pressure resistance for hydrogen storage. To meet the high driving range requirements of hydrogen fuel cell vehicles, the hydrogen pressure inside the composite material storage cylinders is as high as 35-70 MPa. Due to the high pressure, spontaneous combustion, and explosiveness of hydrogen, as well as the flammability of composite materials, hydrogen fuel cell vehicles carrying high-pressure composite material hydrogen storage cylinders pose serious safety hazards. In addition to the ultra-high pressure of hydrogen, composite material hydrogen storage cylinders also face safety issues such as hydrogen damage, leakage, spontaneous combustion, detonation, and the flammability, pyrolysis, and material degradation of the composite material winding layer.

[0003] Chinese patent CN110345380A discloses a gas manifold that provides reliable support and fixation for hydrogen storage containers, thereby improving the safety level when multiple hydrogen storage containers are used in a group. Chinese patent CN110701482A discloses automatic valve actuation and hydrogen pressure detection, with a controller capable of timely detecting overpressure, overflow, and underpressure issues during operation. Chinese patent CN208630361U discloses a method that reduces the pressure of stored high-pressure hydrogen through a pressure reducer and delivers it to the fuel cell in a timely manner, based on the fuel cell's hydrogen pressure requirements.

[0004] The aforementioned existing technologies only address hydrogen leakage prevention at the structural level, and the monitoring of hydrogen leakage only targets the entire hydrogen storage system or the whole vehicle. Therefore, how to monitor hydrogen leakage at specific components or locations is a problem that urgently needs to be solved. Summary of the Invention

[0005] In view of the shortcomings of the prior art described above, the purpose of this application is to provide a method, device, equipment and medium for monitoring hydrogen leakage in fuel cell vehicles, so as to solve the problem of how to monitor hydrogen leakage for specific components or locations in the prior art.

[0006] To achieve the above and other related objectives, this application provides a method for monitoring hydrogen leakage in a fuel cell vehicle, the method comprising:

[0007] The hydrogen leakage change characteristic data at multiple locations pre-set in the fuel cell vehicle are obtained, including hydrogen leakage change data in the vehicle compartment and hydrogen leakage change characteristic data in the hydrogen transportation system.

[0008] According to the preset data specifications, the hydrogen leakage change characteristic data at the multiple locations are preprocessed to obtain the preprocessed hydrogen leakage change characteristic data at the multiple locations.

[0009] The hydrogen leakage change feature data at multiple locations after preprocessing are transmitted to a pre-trained hydrogen leakage monitoring model to obtain hydrogen leakage monitoring results, which include hydrogen leakage level and hydrogen leakage location.

[0010] In one embodiment of this application, the hydrogen leakage change characteristic data at the plurality of locations includes hydrogen leakage change data inside the vehicle cabin. Obtaining the hydrogen leakage change data inside the vehicle cabin includes:

[0011] By using a hydrogen concentration sensor pre-installed in the hydrogen cylinder storage compartment, characteristic data of hydrogen concentration changes in the hydrogen cylinder storage compartment can be obtained.

[0012] By using a hydrogen concentration sensor pre-installed in the engine compartment, characteristic data of hydrogen concentration changes in the engine compartment can be obtained.

[0013] By using a hydrogen concentration sensor pre-installed in the trunk, characteristic data of hydrogen concentration changes in the trunk can be obtained.

[0014] The characteristic data of hydrogen concentration change in the crew cabin are obtained by using hydrogen concentration sensors pre-installed in the crew cabin.

[0015] In one embodiment of this application, the hydrogen leakage change characteristic data at the plurality of locations includes hydrogen leakage change characteristic data in the hydrogen transportation system. Obtaining the hydrogen leakage change characteristic data in the hydrogen transportation system includes:

[0016] Temperature change characteristic data of the hydrogen transport pipeline are obtained by using temperature sensors pre-installed in the hydrogen transport pipeline;

[0017] High pressure change characteristic data are obtained by using a high-pressure sensor pre-installed at the hydrogen release point of the hydrogen cylinder;

[0018] By using a medium-pressure sensor pre-set before hydrogen is introduced into the fuel cell stack, characteristic data of medium-pressure changes are obtained.

[0019] In one embodiment of this application, obtaining hydrogen leakage change characteristic data in the hydrogen transportation system further includes:

[0020] The initial temperature difference and the current temperature difference between the hot-wire anemometer chip and the hydrogen transport environment are obtained by using a hot-wire anemometer sensor pre-installed at the hydrogen cylinder valve.

[0021] Based on the initial temperature difference, the current temperature difference, and the preset correspondence between temperature difference and power, the initial power and the current power of the hot-wire anemometer are determined.

[0022] Based on the correspondence between the initial power, the current power, and the preset power change value and the hydrogen concentration at the hydrogen cylinder valve, the characteristic data of the hydrogen concentration change at the hydrogen cylinder valve are determined.

[0023] In one embodiment of this application, the preset temperature difference and power correspondence is expressed as follows: P = (A + BU) 0.5 )ΔT, where P is the power, A and B are constants determined by the size of the hot-wire anemometer and the properties of the fluid, and ΔT is the temperature difference.

[0024] In one embodiment of this application, based on the correspondence between the initial power, the current power, and the preset power change value and the hydrogen concentration at the hydrogen cylinder valve, characteristic data of the hydrogen concentration change at the hydrogen cylinder valve are determined, including:

[0025] Based on the current power, calculate the power change value in the previous second.

[0026] If the relative error between the initial power and the power change value in the previous second is less than a preset error threshold, then the power change value is determined based on the initial power and the current power.

[0027] Based on the power change value and the preset correspondence between the power change value and the wind speed, the wind speed corresponding to the power change value is obtained;

[0028] Based on the wind speed corresponding to the power change value, the preset wind speed and the hydrogen concentration at the hydrogen cylinder valve, the characteristic data of the hydrogen concentration change at the hydrogen cylinder valve are obtained.

[0029] In one embodiment of this application, before transmitting the preprocessed hydrogen leakage change feature data from multiple locations to a pre-trained hydrogen leakage monitoring model, the method further includes:

[0030] Acquire raw hydrogen leakage change characteristic data at multiple pre-defined locations inside the fuel cell vehicle, and add hydrogen leakage level labels and hydrogen leakage location labels to the raw hydrogen leakage change characteristic data.

[0031] The original hydrogen leakage change characteristic data is preprocessed according to the preset data specifications to obtain the preprocessed data. The preprocessing includes normalization. The data range of the preprocessed data corresponds to the data range of the data output by the pre-trained hydrogen leakage monitoring model.

[0032] According to the preset clustering algorithm, the preprocessed original data is clustered to obtain the clustered data;

[0033] The clustered data is input into a pre-built neural network. The pre-built neural network is trained according to the hydrogen leak level label and the hydrogen leak location label to update the weights of the pre-built neural network and obtain the trained hydrogen leak monitoring model.

[0034] In one embodiment of this application, a hydrogen leakage monitoring device for a fuel cell vehicle is also provided, the device comprising:

[0035] The data acquisition module is used to acquire hydrogen leakage change characteristic data at multiple locations pre-set in the fuel cell vehicle. The hydrogen leakage change characteristic data at multiple locations includes hydrogen leakage change data in the vehicle compartment and hydrogen leakage change characteristic data in the hydrogen transportation system.

[0036] The preprocessing module is used to preprocess the hydrogen leakage change characteristic data at the multiple locations according to the preset data specifications, so as to obtain the preprocessed hydrogen leakage change characteristic data at the multiple locations.

[0037] The leakage monitoring module is used to transmit the pre-processed hydrogen leakage change feature data from multiple locations to a pre-trained hydrogen leakage monitoring model to obtain hydrogen leakage monitoring results, which include hydrogen leakage level and hydrogen leakage location.

[0038] In one embodiment of this application, an electronic device is also provided, the electronic device comprising:

[0039] One or more processors;

[0040] A storage device for storing one or more programs, which, when executed by one or more processors, cause the electronic device to implement the hydrogen leak monitoring method for fuel cell vehicles as described above.

[0041] In one embodiment of this application, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a computer processor, causes the computer to perform the hydrogen leakage monitoring method for fuel cell vehicles as described above.

[0042] The beneficial effects of this invention are:

[0043] First, hydrogen leakage variation characteristic data at multiple pre-defined locations within the fuel cell vehicle are acquired. This data includes hydrogen leakage variation data within the vehicle cabin and hydrogen leakage variation characteristic data within the hydrogen transportation system. The hydrogen leakage variation characteristic data at these locations is preprocessed according to preset data specifications to obtain preprocessed hydrogen leakage variation characteristic data for each location. This preprocessed data is then transmitted to a pre-trained hydrogen leakage monitoring model to obtain hydrogen leakage monitoring results, which include the hydrogen leakage level and location. This invention improves the accuracy of hydrogen leakage monitoring results by using hydrogen leakage variation characteristic data from multiple locations and a pre-trained hydrogen leakage monitoring model to determine the hydrogen leakage level and location.

[0044] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0045] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0046] Figure 1 This is a schematic diagram illustrating the implementation environment of a hydrogen leakage monitoring method for fuel cell vehicles, as shown in an exemplary embodiment of this application.

[0047] Figure 2 This is a schematic flowchart illustrating a hydrogen leakage monitoring method for fuel cell vehicles, as shown in an exemplary embodiment of this application.

[0048] Figure 3 This is an exemplary embodiment of the present application illustrating the assembly of the hydrogen cylinder valve base of a fuel cell vehicle;

[0049] Figure 4 This is a schematic diagram of a hot-wire anemometer shown in an exemplary embodiment of this application;

[0050] Figure 5 This is a block diagram illustrating a hydrogen leak monitoring device for a fuel cell vehicle, as shown in an exemplary embodiment of this application.

[0051] Figure 6 A schematic diagram of the structure of a computer system suitable for an electronic device according to an embodiment of this application is shown;

[0052] In the diagram, 1-high-pressure hydrogen cylinder, 2-hydrogen concentration sensor at the cylinder, 3-temperature sensor, 4-overflow valve, 5-solenoid valve, 6-inlet filter valve, 7-high-pressure sensor, 8-three-way storage chamber, 9-one-way valve, 10-hydrogen filling port, 11-pressure reducing valve, 12-medium-pressure sensor, 13-fuel stack, 14-engine compartment hydrogen concentration sensor, 15-trunk compartment hydrogen concentration sensor, 16-passenger compartment area hydrogen concentration sensor, 17-hydrogen system management controller, 18-hot-wire anemometer chip sensor, 19-cylinder valve seat, 20-hydrogen storage cylinder opening, 21-internal cross-sectional view of the hydrogen storage cylinder, 22-contact surface between the cylinder valve seat and the hydrogen cylinder. Detailed Implementation

[0053] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0054] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0055] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0056] First, it's important to clarify that leaks and explosions in hydrogen storage cylinders are caused by a combination of external thermal loads and internal mechanical loads generated by fire conditions. Most leaks in hydrogen storage cylinder valves occur at the valve opening, where the valve seat connects to the cylinder body. Due to the frequent filling and discharging characteristics of hydrogen-using environments and external vibrations and high temperatures, hydrogen can leak from the valve opening. Therefore, monitoring and assessing leaks at the valve opening and overall vehicle hydrogen leakage is a crucial and paramount aspect of ensuring safe hydrogen storage and use in vehicles.

[0057] Figure 1This is a schematic diagram illustrating the implementation environment of a hydrogen leakage monitoring method for fuel cell vehicles, as shown in an exemplary embodiment of this application. Figure 1 As shown, high-pressure hydrogen cylinder 1 is placed in the hydrogen cylinder storage compartment, and a hydrogen concentration sensor 2 is installed at the corresponding position of the high-pressure hydrogen cylinder 1 to obtain characteristic data of hydrogen concentration changes in the engine compartment. A temperature sensor 3 is placed in the hydrogen storage and supply pipeline and positioned in front of the high-pressure hydrogen cylinder 1 to obtain characteristic data of temperature changes in the hydrogen transport pipeline. An overflow valve 4, a solenoid valve 5, and an inlet filter valve 6 are sequentially connected to the hydrogen transport system via high-pressure pipelines to control the hydrogen charging and discharging process. The overflow valve 4 is similar to a one-way valve, designed to prevent overcharging of hydrogen; the solenoid valve 5 controls the entry and exit path of hydrogen in the pipeline; and the inlet filter valve 6 filters out minor impurities in the hydrogen. A high-pressure sensor 7 is located on the three-way storage chamber 8 where hydrogen is released, used to detect high-pressure changes in the pipeline after the high-pressure hydrogen cylinder 1. A one-way valve 9 is located after the hydrogen filling port 10 and is the only path for high-pressure hydrogen to enter the high-pressure hydrogen cylinder 1. The pressure reducing valve 11, connected after the 8-way storage chamber, is a key component for reducing the pressure of high-pressure hydrogen. A medium-pressure sensor 12 is connected after the pressure reducing valve 11 to monitor the medium-pressure change characteristics before the hydrogen enters the fuel cell stack 13. The fuel cell stack 13 has a hydrogen inlet and a hydrogen outlet.

[0058] Sensors are also incorporated into the entire fuel cell vehicle architecture and hydrogen transportation system to detect changes in hydrogen leakage within the vehicle compartment. See also Figure 1 The engine compartment hydrogen concentration sensor 14 is installed in the engine compartment to obtain characteristic data of hydrogen concentration changes in the engine compartment; the trunk hydrogen concentration sensor 15 is installed in the trunk of the fuel cell vehicle to obtain characteristic data of hydrogen concentration changes in the trunk; and the passenger compartment hydrogen concentration sensor 16 is installed in the passenger compartment to obtain characteristic data of hydrogen concentration changes in the passenger compartment.

[0059] in addition, Figure 1 In the illustrated implementation environment, the hydrogen system management controller 17 is the communication monitoring module for the hydrogen concentration sensor, capable of data processing, analysis, and issuing related commands. A hot-wire anemometer 18 is installed at the valve position of the high-pressure hydrogen cylinder 1 to monitor changes in hydrogen concentration at that location.

[0060] The hydrogen leakage monitoring method for fuel cell vehicles in this embodiment can be implemented, for example, through a hydrogen system management controller 17, by performing the following steps: acquiring hydrogen leakage change characteristic data at multiple pre-defined locations within the fuel cell vehicle, including hydrogen leakage change data within the vehicle compartment and hydrogen leakage change characteristic data in the hydrogen transportation system; preprocessing the hydrogen leakage change characteristic data at the multiple locations according to a preset data specification to obtain preprocessed hydrogen leakage change characteristic data at the multiple locations; transmitting the preprocessed hydrogen leakage change characteristic data at the multiple locations to a pre-trained hydrogen leakage monitoring model to obtain hydrogen leakage monitoring results, including the hydrogen leakage level and the location of the hydrogen leakage. By using hydrogen leakage change characteristic data at multiple locations and a pre-trained hydrogen leakage monitoring model to determine the hydrogen leakage level and location, the accuracy of the hydrogen leakage monitoring results is improved.

[0061] To address the problem of how to monitor hydrogen leaks for specific components or locations in the prior art, embodiments of this application propose a hydrogen leak monitoring method for fuel cell vehicles, a hydrogen leak monitoring device for fuel cell vehicles, an electronic device, a computer-readable storage medium, and a computer program product, which will be described in detail below.

[0062] Please see Figure 2 , Figure 2 This is a schematic flowchart illustrating an exemplary embodiment of a hydrogen leak monitoring method for fuel cell vehicles, which can be applied to... Figure 1 The implementation environment is shown. It should be understood that this method can also be applied to other exemplary implementation environments and specifically executed by devices in other implementation environments. This embodiment does not limit the implementation environment to which the method is applicable.

[0063] like Figure 2 As shown, in an exemplary embodiment, the hydrogen leakage monitoring method for fuel cell vehicles includes at least steps S210 to S230, which are described in detail below:

[0064] In step S210, hydrogen leakage change characteristic data at multiple pre-set locations inside the fuel cell vehicle are acquired.

[0065] First, it should be noted that the hydrogen leakage change characteristics data at multiple locations include hydrogen leakage change data inside the vehicle compartment and hydrogen leakage change characteristics data in the hydrogen transportation system.

[0066] For example, the hydrogen system management controller 17 acquires hydrogen leakage change data through hydrogen concentration sensors 2 at the gas cylinders in the vehicle compartment, 14 in the engine compartment, 15 in the trunk, and 16 in the passenger compartment area. Additionally, the hydrogen system management controller 17 acquires hydrogen leakage change data through temperature sensors 3, high-pressure sensors 7, medium-pressure sensors 12, and hot-wire anemometers 18 installed in the hydrogen transportation system.

[0067] See Figure 3 , Figure 3 This is an exemplary embodiment of the present application illustrating the assembly of the hydrogen cylinder valve base in a fuel cell vehicle. The cylinder valve seat 19 and the hydrogen storage cylinder neck 20 are connected by threads, and multiple gaskets are internally used to achieve a good seal. The internal connection method is shown in the internal sectional view 21 of the hydrogen storage cylinder, which specifically illustrates the internal connection structure. After the cylinder valve seat 19 and the hydrogen storage cylinder neck 20 are connected, a contact surface is formed, which is... Figure 3 The contact surface 22 between the valve seat 19 and the hydrogen cylinder opening 20 is as follows. Since the valve seat 19 and the hydrogen cylinder opening 20 are connected by threads, the connection process can lead to insufficient connection. Due to the manufacturing process and the repeated filling and discharging characteristics of the hydrogen cylinder, the gasket in the threaded opening will fail, causing leakage of high-pressure hydrogen from the hydrogen cylinder opening 2. Therefore, in this embodiment, in addition to detecting the hydrogen concentration in the hydrogen cylinder storage compartment using a hydrogen concentration sensor at the cylinder, a hot-wire anemometer 18 is also used to acquire hydrogen leakage change data to ensure the accuracy of the hydrogen leakage change data and thus improve the precision of the monitoring results.

[0068] In step S220, hydrogen leakage change characteristic data at multiple locations are preprocessed according to preset data specifications to obtain preprocessed hydrogen leakage change characteristic data at multiple locations.

[0069] It should be noted that in this embodiment, the hydrogen leakage change feature data is processed based on a bp neural network. The weights of the network are knowledge of the hydrogen leakage change feature data, the hydrogen leakage level, and the rule diagnosis between the hydrogen leakage location and the leakage level at each location. The leakage level at each location will cause changes in the hydrogen leakage change feature data of the system.

[0070] Because the amplitudes of the directly measured raw data vary considerably, large fluctuations in data values ​​would monopolize the learning process of the neural network without processing, failing to reflect changes in smaller data values ​​and resulting in poor network performance. Furthermore, the network learns the relative importance of variables by adjusting the weights; if the amplitudes of the input variables differ significantly, the weights will also differ greatly during network learning. However, the network's weight range is limited and cannot adapt to such a wide range of data variations. Therefore, preprocessing of the hydrogen leak variation characteristic data is necessary to ensure that the network weights are within a reasonable range, reducing the difficulty of network training. The nonlinear transfer function in the neural network has a range of [-1, 1] or [0, 1], which can be used to transform the hydrogen leak variation characteristic data to fall within this range.

[0071] It is worth noting that the range of each hydrogen leakage change characteristic data is [a, b], where a represents the lower limit and b represents the upper limit.

[0072] In step S230, the hydrogen leakage change feature data at multiple locations after preprocessing are transmitted to a pre-trained hydrogen leakage monitoring model to obtain hydrogen leakage monitoring results.

[0073] It should be noted that the hydrogen leak monitoring results include the hydrogen leak level and the location of the hydrogen leak.

[0074] For example, a hydrogen leak monitoring model based on FCM clustering algorithm and bp neural network acquires hydrogen leak change feature data at multiple locations after preprocessing, and uses Gaussian kernel function for spatial mapping to realize the monitoring of hydrogen leak level and hydrogen leak location.

[0075] As can be seen from steps S210 to S240 above, the solution proposed in this embodiment improves the accuracy of hydrogen leak monitoring results by using hydrogen leak change characteristic data from multiple locations and a pre-trained hydrogen leak monitoring model to determine the hydrogen leak level and location.

[0076] In one embodiment of this application, the hydrogen leakage change characteristic data at multiple locations includes hydrogen leakage change data inside the vehicle cabin. Figure 2 The step S210 shown above, which involves obtaining hydrogen leakage change data in the vehicle compartment, includes the following steps:

[0077] By using a hydrogen concentration sensor pre-installed in the hydrogen cylinder storage compartment, characteristic data of hydrogen concentration changes in the hydrogen cylinder storage compartment can be obtained.

[0078] By using a hydrogen concentration sensor pre-installed in the engine compartment, characteristic data of hydrogen concentration changes in the engine compartment can be obtained.

[0079] By using a hydrogen concentration sensor pre-installed in the trunk, characteristic data of hydrogen concentration changes in the trunk can be obtained.

[0080] The characteristic data of hydrogen concentration change in the crew cabin are obtained by using hydrogen concentration sensors pre-installed in the crew cabin.

[0081] In one embodiment of this application, the hydrogen leakage change characteristic data at multiple locations includes hydrogen leakage change characteristic data in a hydrogen transportation system. Figure 2 Step S210, which involves obtaining hydrogen leakage change characteristic data in the hydrogen transportation system, includes the following steps:

[0082] Temperature change characteristic data of the hydrogen transport pipeline are obtained by using temperature sensors pre-installed in the hydrogen transport pipeline;

[0083] High pressure change characteristic data are obtained by using a high-pressure sensor pre-installed at the hydrogen release point of the hydrogen cylinder;

[0084] By using a medium-pressure sensor pre-set before hydrogen is introduced into the fuel cell stack, characteristic data of medium-pressure changes are obtained.

[0085] In one embodiment of this application, in Figure 1 Step S210, which involves obtaining hydrogen leakage change characteristic data in the hydrogen transportation system, further includes the following steps:

[0086] The initial temperature difference and the current temperature difference between the hot-wire anemometer chip and the hydrogen transport environment are obtained by using a hot-wire anemometer sensor pre-installed at the hydrogen cylinder valve.

[0087] Based on the initial temperature difference, the current temperature difference, and the preset correspondence between temperature difference and power, the initial power and the current power of the hot-wire anemometer are determined.

[0088] Based on the correspondence between the initial power, the current power, and the preset power change value and the hydrogen concentration at the hydrogen cylinder valve, the characteristic data of the hydrogen concentration change at the hydrogen cylinder valve are determined.

[0089] See Figure 4 , Figure 4 This is a schematic diagram of a hot-wire anemometer, illustrating an exemplary embodiment of this application. When the hot-wire anemometer is in operation, a heating source first provides heating power, creating a stable heat distribution on the surface of the sensor chip. Under the influence of the external wind field being measured on the chip's temperature field, a corresponding measurement temperature field is formed on the chip surface. This temperature field is converted into an electrical signal through thermoelectric coupling, and finally processed into measured wind field data.

[0090] The second law of thermodynamics states that heat can spontaneously transfer from a high-temperature object to a low-temperature object, driven by a temperature difference. Heat transfer primarily occurs through three forms: conduction, convection, and radiation. In opaque solids, only conduction occurs; in transparent or translucent solids, both conduction and radiation can occur simultaneously; and in liquids and gases, all three can occur concurrently. In hot-wire anemometers, heat is transferred between the solid-state chip and the air during operation.

[0091] For the measurement of hydrogen leakage at the cylinder valve, refer to Figure 1 The instantaneous output power of hydrogen at the cylinder valve can be obtained by attaching a hot-wire anemometer 18 to the high-pressure hydrogen cylinder 1, and the quantitative analysis of the instantaneous output power of hydrogen at the cylinder valve can be completed by the following formula: P = (A + BU) 0.5 )ΔT, where P is the power, A and B are constants determined by the size of the hot-wire anemometer and the properties of the fluid, and ΔT is the temperature difference.

[0092] Heat loss anemometers primarily operate in two modes: constant power and constant temperature difference. In constant power mode, the total heating power P is constant, and the flow rate is reflected by temperature changes. In constant temperature difference mode, the temperature difference between the chip and the environment is constant, and the flow rate is reflected by power changes.

[0093] In one embodiment of this application, the characteristic data of hydrogen concentration change at the hydrogen cylinder valve are determined based on the correspondence between the initial power, the current power, and the preset power change value and the hydrogen concentration at the hydrogen cylinder valve. This includes the following steps:

[0094] Based on the current power, calculate the power change value in the previous second.

[0095] If the relative error between the initial power and the power change value in the previous second is less than a preset error threshold, then the power change value is determined based on the initial power and the current power.

[0096] Based on the power change value and the preset correspondence between the power change value and the wind speed, the wind speed corresponding to the power change value is obtained;

[0097] Based on the wind speed corresponding to the power change value, the preset wind speed and the hydrogen concentration at the hydrogen cylinder valve, the characteristic data of the hydrogen concentration change at the hydrogen cylinder valve are obtained.

[0098] For example, by utilizing the simulated changes in wind speed and power, a correspondence between wind speed and power changes is established. In actual use, if a hydrogen leak occurs, the hydrogen system management controller 17 can determine the leakage amount in real time by internally searching a MAP (map) between the power change value and the wind speed. The specific formulas are as follows: Y = f(Δp); ΔQ = f(Y). Here, f represents a mapping relationship, which can be determined through offline experiments or by establishing a MAP through calibration. Furthermore, after determining the wind speed through the power change value, the characteristic data of the hydrogen concentration change at the hydrogen cylinder valve can be obtained based on the correspondence between the wind speed, the preset wind speed, and the hydrogen concentration at the hydrogen cylinder valve.

[0099] For example, the hydrogen concentration determination process using a hot-wire anemometer includes the following steps:

[0100] a. Records as follows Figure 1 The output power of the hydrogen system management controller 17 of the hot-wire anemometer 18;

[0101] b. Starting from the current moment, calculate the power change value within the previous second. The calculation method for the power change value is as follows: N = 1…60, where, This represents the power change value;

[0102] c. Calculate whether the relative error between the initial power and the power change value within one second prior to the current time exceeds a preset error threshold. Preferably, the preset error threshold can be selected as 5%. If the relative error exceeds the preset error threshold, the power fluctuation error within one second is repeatedly calculated. If the relative error is less than the preset error threshold, the power change value is determined based on the initial power and the current power. The relative error is calculated as follows:

[0103] d. Calculate the power change value. The power change value is calculated as ΔP = P T -P0;

[0104] e. Locate the MAP plot showing the relationship between power change values ​​and wind speed.

[0105] In one embodiment of this application, Figure 1 Before transmitting the preprocessed hydrogen leakage change feature data from multiple locations to the pre-trained hydrogen leakage monitoring model in step S230, the following steps are also included:

[0106] Acquire raw hydrogen leakage change characteristic data at multiple pre-defined locations inside the fuel cell vehicle, and add hydrogen leakage level labels and hydrogen leakage location labels to the raw hydrogen leakage change characteristic data.

[0107] The original hydrogen leakage change characteristic data is preprocessed according to the preset data specifications to obtain the preprocessed data. The preprocessing includes normalization. The data range of the preprocessed data corresponds to the data range of the data output by the pre-trained hydrogen leakage monitoring model.

[0108] According to the preset clustering algorithm, the preprocessed original data is clustered to obtain the clustered data;

[0109] The clustered data is input into a pre-built neural network. The pre-built neural network is trained according to the hydrogen leak level label and the hydrogen leak location label to update the weights of the pre-built neural network and obtain the trained hydrogen leak monitoring model.

[0110] In this embodiment, hydrogen leakage monitoring for fuel cell vehicles is implemented based on the FCM clustering algorithm and the BP neural network algorithm. Clustering analysis is used to achieve predictive clustering of real-time data, enabling hierarchical classification prediction. Clustering analysis is an analytical process that groups a set of physical or abstract objects into multiple classes composed of similar objects. Assuming that data X contains n samples, denoted as Xk (k = 1, 2, ..., n), the clustering problem is to divide (X1, X2, ..., Xn) into c subsets of X, where 2 ≤ c ≤ n. Similar samples should ideally be in the same class, while dissimilar samples should be in different classes. The number of clusters c may be unknown beforehand. For a set of feature values ​​from network performance tests, fuzzy clustering is used to obtain the cluster centers of the feature values ​​in the feature space. The degree of performance deviation or the possible type and level of the fault is determined by calculating the "distance" between the feature locations and each cluster center.

[0111] Figure 5 This is a block diagram illustrating a hydrogen leak monitoring device for a fuel cell vehicle, as shown in an exemplary embodiment of this application. The device can be applied to… Figure 1 The implementation environment shown is not limited to this embodiment. This device can also be applied to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the device is applicable.

[0112] like Figure 5 As shown, this exemplary hydrogen leak monitoring device for a fuel cell vehicle includes:

[0113] The data acquisition module 501 is used to acquire hydrogen leakage change characteristic data at multiple locations preset in the fuel cell vehicle. The hydrogen leakage change characteristic data at multiple locations includes hydrogen leakage change data in the vehicle compartment and hydrogen leakage change characteristic data in the hydrogen transportation system.

[0114] The preprocessing module 502 is used to preprocess the hydrogen leakage change characteristic data at the multiple locations according to the preset data specifications, so as to obtain the preprocessed hydrogen leakage change characteristic data at the multiple locations.

[0115] The leakage monitoring module 503 is used to transmit the pre-processed hydrogen leakage change feature data at multiple locations to a pre-trained hydrogen leakage monitoring model to obtain hydrogen leakage monitoring results, which include hydrogen leakage level and hydrogen leakage location.

[0116] In this exemplary hydrogen leak monitoring device for fuel cell vehicles, ...

[0117] In another exemplary embodiment, the data acquisition module 501 includes a hydrogen leakage change data acquisition unit in the vehicle cabin, which is configured to:

[0118] By using a hydrogen concentration sensor pre-installed in the hydrogen cylinder storage compartment, characteristic data of hydrogen concentration changes in the hydrogen cylinder storage compartment can be obtained.

[0119] By using a hydrogen concentration sensor pre-installed in the engine compartment, characteristic data of hydrogen concentration changes in the engine compartment can be obtained.

[0120] By using a hydrogen concentration sensor pre-installed in the trunk, characteristic data of hydrogen concentration changes in the trunk can be obtained.

[0121] The characteristic data of hydrogen concentration change in the crew cabin are obtained by using hydrogen concentration sensors pre-installed in the crew cabin.

[0122] In another exemplary embodiment, the data acquisition module 501 includes a hydrogen leakage change characteristic data acquisition unit for a hydrogen transportation system, the hydrogen leakage change characteristic data acquisition unit for a hydrogen transportation system being configured to:

[0123] Temperature change characteristic data of the hydrogen transport pipeline are obtained by using temperature sensors pre-installed in the hydrogen transport pipeline;

[0124] High pressure change characteristic data are obtained by using a high-pressure sensor pre-installed at the hydrogen release point of the hydrogen cylinder;

[0125] By using a medium-pressure sensor pre-set before hydrogen is introduced into the fuel cell stack, characteristic data of medium-pressure changes are obtained.

[0126] In another exemplary embodiment, the hydrogen leakage change characteristic data acquisition unit of the hydrogen transportation system is further configured to:

[0127] The initial temperature difference and the current temperature difference between the hot-wire anemometer chip and the hydrogen transport environment are obtained by using a hot-wire anemometer sensor pre-installed at the hydrogen cylinder valve.

[0128] Based on the initial temperature difference, the current temperature difference, and the preset correspondence between temperature difference and power, the initial power and the current power of the hot-wire anemometer are determined.

[0129] Based on the correspondence between the initial power, the current power, and the preset power change value and the hydrogen concentration at the hydrogen cylinder valve, the characteristic data of the hydrogen concentration change at the hydrogen cylinder valve are determined.

[0130] In another exemplary embodiment, the hydrogen leakage change characteristic data acquisition unit of the hydrogen transportation system is further configured to:

[0131] Based on the current power, calculate the power change value in the previous second.

[0132] If the relative error between the initial power and the power change value in the previous second is less than a preset error threshold, then the power change value is determined based on the initial power and the current power.

[0133] Based on the power change value and the preset correspondence between the power change value and the wind speed, the wind speed corresponding to the power change value is obtained;

[0134] Based on the wind speed corresponding to the power change value, the preset wind speed and the hydrogen concentration at the hydrogen cylinder valve, the characteristic data of the hydrogen concentration change at the hydrogen cylinder valve are obtained.

[0135] In another exemplary embodiment, the hydrogen leak monitoring device for fuel cell vehicles further includes a model training module, which is configured to:

[0136] Acquire raw hydrogen leakage change characteristic data at multiple pre-defined locations inside the fuel cell vehicle, and add hydrogen leakage level labels and hydrogen leakage location labels to the raw hydrogen leakage change characteristic data.

[0137] The original hydrogen leakage change characteristic data is preprocessed according to the preset data specifications to obtain the preprocessed data. The preprocessing includes normalization. The data range of the preprocessed data corresponds to the data range of the data output by the pre-trained hydrogen leakage monitoring model.

[0138] According to the preset clustering algorithm, the preprocessed original data is clustered to obtain the clustered data;

[0139] The clustered data is input into a pre-built neural network. The pre-built neural network is trained according to the hydrogen leak level label and the hydrogen leak location label to update the weights of the pre-built neural network and obtain the trained hydrogen leak monitoring model.

[0140] It should be noted that the hydrogen leakage monitoring device for fuel cell vehicles provided in the above embodiments and the hydrogen leakage monitoring method for fuel cell vehicles provided in the above embodiments belong to the same concept. The specific operation methods of each module and unit have been described in detail in the method embodiments and will not be repeated here. In practical applications, the road condition refresh device provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation here.

[0141] Embodiments of this application also provide an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the hydrogen leakage monitoring method for fuel cell vehicles provided in the above embodiments.

[0142] Figure 6 A schematic diagram of a computer system suitable for an electronic device according to an embodiment of this application is shown. It should be noted that... Figure 6 The computer system 600 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0143] like Figure 6 As shown, the computer system 600 includes a Central Processing Unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 602 or programs loaded from Storage Unit 608 into Random Access Memory (RAM) 603, such as performing the methods described in the above embodiments. The RAM 603 also stores various programs and data required for system operation. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An Input / Output (I / O) interface 605 is also connected to the bus 604.

[0144] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0145] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs various functions defined in the system of this application.

[0146] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0147] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0148] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0149] Another aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a computer's processor, causes the computer to perform the aforementioned method for monitoring hydrogen leaks in a fuel cell vehicle. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not incorporated into the electronic device.

[0150] Another aspect of this application provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the hydrogen leak monitoring method for fuel cell vehicles provided in the various embodiments described above.

[0151] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A method for monitoring hydrogen leakage in a fuel cell vehicle, characterized in that, The method includes: The hydrogen leakage change characteristic data at multiple locations pre-set in the fuel cell vehicle are obtained, including hydrogen leakage change data in the vehicle compartment and hydrogen leakage change characteristic data in the hydrogen transportation system. According to the preset data specifications, the hydrogen leakage change characteristic data at the multiple locations are preprocessed to obtain the preprocessed hydrogen leakage change characteristic data at the multiple locations. The hydrogen leakage change feature data at multiple locations after preprocessing are transmitted to a pre-trained hydrogen leakage monitoring model to obtain hydrogen leakage monitoring results, which include hydrogen leakage level and hydrogen leakage location. Acquiring hydrogen leakage change data within the vehicle compartment includes: obtaining characteristic data on hydrogen concentration changes in the hydrogen cylinder storage compartment using a hydrogen concentration sensor pre-installed in the hydrogen cylinder storage compartment; obtaining characteristic data on hydrogen concentration changes in the engine compartment using a hydrogen concentration sensor pre-installed in the engine compartment; obtaining characteristic data on hydrogen concentration changes in the trunk using a hydrogen concentration sensor pre-installed in the trunk; and obtaining characteristic data on hydrogen concentration changes in the passenger compartment using a hydrogen concentration sensor pre-installed in the passenger compartment. Acquiring hydrogen leakage change characteristic data in the hydrogen transportation system includes: obtaining the initial temperature difference and the current temperature difference between the hot-wire anemometer chip and the hydrogen transportation environment using a hot-wire anemometer pre-installed at the hydrogen cylinder valve; determining the initial power and current power of the hot-wire anemometer based on the initial temperature difference, the current temperature difference, and a preset correspondence between the temperature difference and power; and determining the hydrogen concentration change characteristic data at the hydrogen cylinder valve based on the initial power, the current power, and a preset correspondence between the power change value and the hydrogen concentration at the hydrogen cylinder valve. Acquiring hydrogen leakage change characteristic data in the hydrogen transportation system further includes: obtaining temperature change characteristic data of the hydrogen transportation pipeline through a temperature sensor pre-installed in the hydrogen transportation pipeline; obtaining high pressure change characteristic data through a high pressure sensor pre-installed at the hydrogen release point of the hydrogen cylinder; and obtaining medium pressure change characteristic data through a medium pressure sensor pre-installed before the hydrogen enters the fuel cell stack.

2. The method for monitoring hydrogen leakage in a fuel cell vehicle according to claim 1, characterized in that, The preset relationship between temperature difference and power is expressed as follows: P = (A + BU) 0.5 )ΔT, where P is the power, A and B are constants determined by the size of the hot-wire anemometer and the properties of the fluid, and ΔT is the temperature difference.

3. The method for monitoring hydrogen leakage in a fuel cell vehicle according to claim 1, characterized in that, Based on the correspondence between the initial power, the current power, and the preset power change value and the hydrogen concentration at the hydrogen cylinder valve, the characteristic data of the hydrogen concentration change at the hydrogen cylinder valve are determined, including: Based on the current power, calculate the power change value in the previous second. If the relative error between the initial power and the power change value in the previous second is less than a preset error threshold, then the power change value is determined based on the initial power and the current power. Based on the power change value and the preset correspondence between the power change value and the wind speed, the wind speed corresponding to the power change value is obtained; Based on the wind speed corresponding to the power change value, the preset wind speed and the hydrogen concentration at the hydrogen cylinder valve, the characteristic data of the hydrogen concentration change at the hydrogen cylinder valve are obtained.

4. The method for monitoring hydrogen leakage in a fuel cell vehicle according to claim 1, characterized in that, Before transmitting the preprocessed hydrogen leakage change feature data from multiple locations to the pre-trained hydrogen leakage monitoring model, the process further includes: Acquire raw hydrogen leakage change characteristic data at multiple pre-defined locations inside the fuel cell vehicle, and add hydrogen leakage level labels and hydrogen leakage location labels to the raw hydrogen leakage change characteristic data. The original hydrogen leakage change characteristic data is preprocessed according to the preset data specifications to obtain the preprocessed data. The preprocessing includes normalization. The data range of the preprocessed data corresponds to the data range of the data output by the pre-trained hydrogen leakage monitoring model. According to the preset clustering algorithm, the preprocessed original data is clustered to obtain the clustered data; The clustered data is input into a pre-built neural network. The pre-built neural network is trained according to the hydrogen leak level label and the hydrogen leak location label to update the weights of the pre-built neural network and obtain the trained hydrogen leak monitoring model.

5. A hydrogen leak monitoring device for fuel cell vehicles, characterized in that, The device includes: The data acquisition module is used to acquire hydrogen leakage change characteristic data at multiple locations pre-set in the fuel cell vehicle. The hydrogen leakage change characteristic data at multiple locations includes hydrogen leakage change data in the vehicle compartment and hydrogen leakage change characteristic data in the hydrogen transportation system. The preprocessing module is used to preprocess the hydrogen leakage change characteristic data at the multiple locations according to the preset data specifications, so as to obtain the preprocessed hydrogen leakage change characteristic data at the multiple locations. The leakage monitoring module is used to transmit the hydrogen leakage change feature data at multiple locations after preprocessing to a pre-trained hydrogen leakage monitoring model to obtain hydrogen leakage monitoring results, which include hydrogen leakage level and hydrogen leakage location. The data acquisition module is specifically used for: Hydrogen concentration change characteristic data in the hydrogen cylinder storage compartment is obtained by using a hydrogen concentration sensor pre-installed in the hydrogen cylinder storage compartment; hydrogen concentration change characteristic data in the engine compartment is obtained by using a hydrogen concentration sensor pre-installed in the engine compartment; hydrogen concentration change characteristic data in the trunk is obtained by using a hydrogen concentration sensor pre-installed in the trunk; and hydrogen concentration change characteristic data in the passenger compartment is obtained by using a hydrogen concentration sensor pre-installed in the passenger compartment. By using a hot-wire anemometer pre-installed at the hydrogen cylinder valve, the initial temperature difference and the current temperature difference between the hot-wire anemometer chip and the hydrogen transport environment are obtained. Based on the initial temperature difference, the current temperature difference, and the preset correspondence between the temperature difference and power, the initial power and the current power of the hot-wire anemometer are determined. Based on the initial power, the current power, and the preset power change value and the hydrogen concentration at the hydrogen cylinder valve, the characteristic data of hydrogen concentration change at the hydrogen cylinder valve are determined. Temperature change characteristic data of the hydrogen transport pipeline is obtained by using a temperature sensor pre-installed in the hydrogen transport pipeline; high pressure change characteristic data is obtained by using a high pressure sensor pre-installed at the hydrogen release point of the hydrogen cylinder; and medium pressure change characteristic data is obtained by using a medium pressure sensor pre-installed before the hydrogen enters the fuel cell stack.

6. An electronic device, characterized in that, The electronic device includes: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the electronic device to implement the hydrogen leak monitoring method for fuel cell vehicles as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by the computer's processor, causes the computer to perform the fuel cell vehicle hydrogen leak monitoring method as described in any one of claims 1 to 4.

Images