A method, system, electronic device, and storage medium for measuring hydrogen leakage rate.

Abstract

This invention discloses a method, system, electronic device, and storage medium for measuring hydrogen leakage rate, relating to the field of hydrogen safety utilization technology. The method includes: calculating the acoustic signal and signal phase difference corresponding to the target device based on an ultrasonic sensor array; obtaining a predicted nozzle aperture based on the acoustic signal, signal phase difference, and a first conversion model determined by a deep learning algorithm; obtaining a predicted gas pressure based on the acoustic signal, signal phase difference, and a second conversion model determined by a deep learning algorithm; and calculating the hydrogen leakage rate at the leak point of the target device based on the predicted nozzle aperture and gas pressure. This invention can accurately predict the hydrogen leakage rate, thus laying the foundation for predicting the amount of hydrogen leakage and the timing of early warnings.

Description

Technical Field

[0001] This invention relates to the field of hydrogen safe utilization technology, and in particular to a method, system, electronic device and storage medium for measuring hydrogen leakage rate based on an ultrasonic sensor. Background Technology

[0002] Due to its high efficiency, cleanliness, and renewability, hydrogen is increasingly attracting attention from government, academia, and industry as an energy source for both storage and supply. However, hydrogen is flammable and explosive, has a high diffusion coefficient, and can easily degrade the mechanical properties of materials. Furthermore, when hydrogen reaches a volume fraction of 4%-75.6% in air, only 0.017 mJ of ignition energy is required to ignite and explode. Potential leaks and explosions exist during hydrogen production, storage, transportation, refueling, and use. Moreover, hydrogen explosions are a combined chain reaction of deflagration and detonation within a diffusion range, with the resulting flame propagation speed approaching the speed of sound. Therefore, studying hydrogen leakage and diffusion patterns and predicting hydrogen leakage rates is of great significance for hydrogen safety research.

[0003] When hydrogen leaks, it rubs against the wall of the leak hole in the container, creating an unstable flow at the outlet. This generates dipole and quadrupole sound sources, producing ultrasonic waves. The turbulence pattern and distribution generated by the leaking hydrogen will change depending on the shape, size, gas properties, and gas pressure of the leak hole, resulting in different characteristics of the generated sound wave signals.

[0004] Ultrasonic gas leak detection technology is a relatively new technology in gas leak detection. As a major method of non-destructive testing, ultrasonic testing technology has advantages such as strong penetration ability, high sensitivity to the target being tested, fast detection speed, and accurate defect location. It is now widely used in non-destructive testing for on-site environments.

[0005] Existing ultrasonic gas leak detection technology can locate the gas leak source based on sound pressure level and time difference of arrival. However, it is difficult to obtain the key parameter of hydrogen leak rate from the sound wave signal obtained by ultrasonic sensors. Summary of the Invention

[0006] The purpose of this invention is to provide a method, system, electronic device, and storage medium for measuring hydrogen leakage rate, which can accurately predict hydrogen leakage rate.

[0007] To achieve the above objectives, the present invention provides the following solution:

[0008] In a first aspect, the present invention provides a method for measuring hydrogen leakage rate based on an ultrasonic sensor, comprising:

[0009] Based on an ultrasonic sensor array, the acoustic signal and signal phase difference corresponding to the target device are calculated; the target device is a device for storing hydrogen.

[0010] The predicted nozzle aperture is obtained based on the acoustic signal, the signal phase difference, and the first conversion model determined by the deep learning algorithm.

[0011] The predicted gas pressure is obtained based on the acoustic signal, the signal phase difference, and the second conversion model determined by a deep learning algorithm.

[0012] The hydrogen leakage rate at the target equipment leak point is calculated based on the predicted nozzle orifice diameter and the gas pressure.

[0013] Secondly, the present invention provides a hydrogen leakage rate measurement system based on an ultrasonic sensor, comprising:

[0014] An acoustic signal and signal phase difference calculation module is used to calculate the acoustic signal and signal phase difference corresponding to a target device based on an ultrasonic sensor array; the target device is a device for storing hydrogen.

[0015] The nozzle aperture prediction module is used to obtain the predicted nozzle aperture based on the acoustic signal, the signal phase difference, and a first conversion model determined based on a deep learning algorithm.

[0016] A gas pressure prediction module is used to obtain the predicted gas pressure based on the acoustic signal, the signal phase difference, and a second conversion model determined based on a deep learning algorithm.

[0017] The hydrogen leakage rate prediction module is used to calculate the hydrogen leakage rate at the leak point of the target equipment based on the predicted nozzle orifice diameter and the gas pressure.

[0018] Thirdly, the present invention provides an electronic device including a memory and a processor, the memory being used to store a computer program, the processor running the computer program to cause the electronic device to perform the hydrogen leakage rate measurement method based on an ultrasonic sensor according to the first aspect.

[0019] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the hydrogen leakage rate measurement method based on an ultrasonic sensor as described in the first aspect.

[0020] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0021] This invention uses an ultrasonic sensor array to determine the acoustic signal and signal phase difference corresponding to the target device; it uses the acoustic signal, signal phase difference, and deep learning algorithm to predict the nozzle aperture and gas pressure; and it uses the nozzle aperture and gas pressure to calculate the hydrogen leakage rate at the leak point of the target device. This solves the problem of difficulty in measuring the internal and external pressure of the pipeline and the leakage aperture, and improves the accuracy of hydrogen leakage rate prediction. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 A schematic flowchart of a hydrogen leakage rate measurement method based on an ultrasonic sensor provided in an embodiment of the present invention;

[0024] Figure 2 This is a schematic diagram of the structure of a hydrogen leakage rate measurement system based on an ultrasonic sensor provided in an embodiment of the present invention. Detailed Implementation

[0025] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0027] Example 1

[0028] like Figure 1 As shown, this embodiment of the invention provides a method for measuring hydrogen leakage rate based on an ultrasonic sensor, including:

[0029] Step 100: Based on the ultrasonic sensor array, calculate the acoustic signal and signal phase difference corresponding to the target device; the target device is a device for storing hydrogen.

[0030] Preferably, multiple ultrasonic sensors are arranged around the target device to form an ultrasonic sensor array; the ultrasonic sensors are used to monitor ultrasonic signals generated when hydrogen leaks; step 100 specifically includes:

[0031] Based on ultrasonic sensor arrays and signal processing technology, the sound pressure signal when ultrasonic waves reach the ultrasonic sensor, as well as the signal phase difference when ultrasonic waves reach different ultrasonic sensors, are obtained.

[0032] Wherein, the acoustic signal corresponding to the target device is the sound pressure signal when the ultrasonic wave reaches the ultrasonic sensor; the signal phase difference corresponding to the target device is the signal phase difference when the ultrasonic wave reaches different ultrasonic sensors.

[0033] Step 200: Based on the acoustic signal, the signal phase difference, and the first conversion model determined by the deep learning algorithm, the predicted nozzle aperture is obtained.

[0034] Step 300: Obtain the predicted gas pressure based on the acoustic signal, the signal phase difference, and the second conversion model determined by the deep learning algorithm.

[0035] Step 400: Calculate the hydrogen leakage rate at the leak point of the target equipment based on the predicted nozzle orifice diameter and the gas pressure.

[0036] Preferred, step 400 specifically includes:

[0037] First, the leakage hole area is calculated based on the predicted nozzle orifice diameter; where the predicted nozzle orifice diameter is the leakage hole diameter. Second, the hydrogen leakage rate is calculated based on the leakage hole area, the predicted gas pressure, and the hydrogen leakage rate calculation formula.

[0038] The formula for calculating the hydrogen leakage rate is:

[0039]

[0040] In the formula, Q is the hydrogen leakage rate, with units of kg / s; A l The area of ​​the leakage hole is expressed in meters (m²). 2 P is the gas pressure at the leak point, in Pa; C D The correction factor for the hydrogen leakage rate at the leak hole; k is the hydrogen adiabatic coefficient, C D k is a constant.

[0041] Furthermore, the method also includes:

[0042] Based on the hydrogen leakage rate at the target equipment leak point over a period of time, a Gaussian process regression algorithm is used to determine the relationship between the hydrogen leakage rate at the target equipment leak point and time in the future period.

[0043] Based on the relationship between the hydrogen leakage rate at the target equipment leak point and time in the future period, the hydrogen leakage amount at each moment corresponding to the leak point in the target equipment in the future period is calculated by integration.

[0044] In chronological order, the predicted hydrogen leakage amount at the target equipment leak point in future time periods is compared with the leakage threshold.

[0045] When the predicted hydrogen leakage amount at the target equipment leak point in the future period exceeds the leakage threshold, the comparison is stopped, and the time corresponding to the predicted hydrogen leakage amount at the target equipment leak point in the future period when the comparison is stopped, along with a hydrogen leakage early warning command, is output to achieve early warning of hydrogen leakage.

[0046] The process of predicting the future hydrogen leakage rate based on the Gaussian process regression algorithm is as follows:

[0047] (1) Select the hydrogen leakage rate over a period of time as the learning sample.

[0048] (2) Select a suitable kernel function, set the initial value of the hyperparameter, and determine the prior model of Gaussian process regression.

[0049] (3) Train the prior model of Gaussian process regression based on the learning samples to determine the posterior model of Gaussian process regression.

[0050] (4) The posterior model based on Gaussian process regression is used to predict the hydrogen leakage rate at future moments.

[0051] Example 2

[0052] In order to implement the method corresponding to Embodiment 1 above and achieve the corresponding functions and technical effects, a hydrogen leakage rate measurement system based on an ultrasonic sensor is provided below.

[0053] like Figure 2 As shown, this embodiment of the invention provides a hydrogen leakage rate measurement system based on an ultrasonic sensor, comprising:

[0054] Acoustic signal and signal phase difference calculation module 1 is used to calculate the acoustic signal and signal phase difference corresponding to the target device based on the ultrasonic sensor array; the target device is a device for storing hydrogen.

[0055] The nozzle aperture prediction module 2 is used to obtain the predicted nozzle aperture based on the acoustic signal, the signal phase difference, and the first conversion model determined based on a deep learning algorithm.

[0056] The gas pressure prediction module 3 is used to obtain the predicted gas pressure based on the acoustic signal, the signal phase difference, and the second conversion model determined based on a deep learning algorithm.

[0057] The hydrogen leakage rate prediction module 4 is used to calculate the hydrogen leakage rate at the leak point of the target equipment based on the predicted nozzle orifice diameter and the gas pressure.

[0058] Furthermore, the system also includes:

[0059] The relationship determination module is used to determine the relationship between the hydrogen leakage rate at the target equipment leak point and time in the future period based on the hydrogen leakage rate at the leak point over a period of time and a Gaussian process regression algorithm.

[0060] The hydrogen leakage prediction module is used to calculate the hydrogen leakage amount at each moment of the target equipment leakage point in the future period based on the relationship between the hydrogen leakage rate and time in the future period.

[0061] The hydrogen leakage time prediction module is used to compare the predicted hydrogen leakage amount at the target equipment leakage point in the future time period with the leakage threshold in chronological order. When the predicted hydrogen leakage amount at the target equipment leakage point in the future time period is greater than the leakage threshold, the comparison stops, and the module outputs the time corresponding to the predicted hydrogen leakage amount at the target equipment leakage point in the future time period when the comparison stops, as well as a hydrogen leakage warning command.

[0062] Example 3

[0063] This invention provides a method for measuring hydrogen leakage rate and assessing hydrogen leakage volume based on ultrasonic sensors. This method can measure the hydrogen leakage rate in pipelines, solving the problem of difficulty in measuring internal and external pressures and leakage orifice diameters. Using the hydrogen leakage rate measured over a period of time, it predicts the hydrogen leakage rate over a future period, thereby assessing when the hydrogen leakage volume will reach a dangerous threshold. This provides early warning of the process from hydrogen leakage to potential safety hazards, improving the safety of hydrogen during transportation and storage. The entire process involves low computational load, high efficiency, is realistic, and highly accurate.

[0064] This invention provides a method for measuring hydrogen leakage rate and assessing hydrogen leakage amount based on an ultrasonic sensor, comprising:

[0065] Step S1: Obtain several sets of training datasets; the training datasets include sound pressure training set, phase difference training set, nozzle aperture training set, and gas pressure training set.

[0066] Specifically, step S1 includes:

[0067] Step S11: Set up the experimental platform; place a pressure sensor at the hydrogen leak point to detect the gas pressure of hydrogen at the leak point; arrange N ultrasonic sensors to form an ultrasonic array, taking an ultrasonic sensor array consisting of 5 ultrasonic sensors as an example below.

[0068] Step S12: Conduct a hydrogen leak experiment. Different nozzle orifice diameters are selected and recorded to obtain a nozzle orifice diameter training set. The gas pressure of hydrogen at the leak point is obtained using a pressure sensor to obtain a gas pressure training set. Ultrasonic sensors are used to monitor the ultrasonic signals generated during the hydrogen leak. Signal processing is performed to obtain the sound pressure signal when the ultrasonic waves reach the ultrasonic sensors, and the phase difference of the ultrasonic waves reaching different ultrasonic sensors, resulting in sound pressure training sets and phase difference training sets. For safety reasons, helium, which has a similar density to hydrogen but is non-flammable and non-explosive, is used instead of hydrogen in the experiment. In this embodiment of the invention, the hydrogen leak duration is set to 5 seconds. The ultrasonic sensor samples the hydrogen leak signal at a sampling frequency of 20 kHz, obtaining 5 sets of sound pressure signal data and 10 sets of phase difference signal data.

[0069] Step S2: Based on the sound pressure training set, phase difference training set, nozzle aperture training set, and deep learning algorithm, a first conversion model is obtained; the input of the first conversion model is sound pressure and phase difference, and the output of the first conversion model is nozzle aperture; based on the sound pressure training set, phase difference training set, gas pressure training set, and deep learning algorithm, a second conversion model is obtained; the input of the second conversion model is sound pressure and phase difference, and the output of the second conversion model is gas pressure.

[0070] Specifically, step S2 includes:

[0071] Step S21: Use 80% of the training dataset for deep learning training and 20% of the training dataset for model testing.

[0072] Step S22: Construct a first conversion network and a second conversion network. Using sound pressure and phase difference as feature inputs and nozzle aperture as the final output, iteratively train the first conversion network. Similarly, iteratively train the second conversion network using sound pressure and phase difference as feature inputs and gas pressure as the final output. The loss function for both the first and second conversion networks is mean squared error, and the activation function is ReLU. A regularization layer is added, combining the regularization loss and mean squared error as the overall error loss value. During backpropagation, the size of both the first and second conversion networks decreases, and all weight coefficients are minimized to reduce the impact of random errors on the final output. Training ends when the error loss value is less than a set error loss value and overfitting does not occur, resulting in the first and second conversion models. In this embodiment, the set error loss value is 5%.

[0073] The formula for calculating the mean square error is as follows:

[0074]

[0075] In the formula: MSE is the mean square error, M is the number of sound pressure and phase differences input in the current iteration, and y1 is the actual gas pressure value corresponding to the sound pressure and phase difference. y1 represents the predicted gas pressure value corresponding to the sound pressure and phase difference, or y1 represents the actual nozzle orifice size value corresponding to the sound pressure and phase difference. This represents the predicted nozzle orifice size corresponding to the sound pressure and phase difference.

[0076] The formula for calculating the regularization loss is as follows:

[0077]

[0078] In the formula: L2 is the regularization loss, Z is the number of weight coefficients, λ is the regularization coefficient, and θ2 is the z-th weight coefficient.

[0079] The formula for calculating the error loss value is as follows:

[0080]

[0081] In the formula: This represents the error loss value.

[0082] Step S3: Based on the ultrasonic sensor array, acquire real-time acoustic signals, such as the sound pressure measured by different ultrasonic sensors and the signal phase difference when the ultrasonic waves reach different ultrasonic sensors. Combine the first conversion model and the second conversion model mentioned above to obtain the predicted nozzle aperture and gas pressure.

[0083] Step S4: Based on the predicted nozzle orifice diameter and gas pressure, the hydrogen leakage rate is calculated.

[0084] Specifically, step S4 includes:

[0085] When hydrogen leaks, the fluid at the leak hole flows at the speed of sound. Based on the momentum equation, energy equation, gas law equation, Poisson's equation, and continuity equation for hydrogen leakage, the formula for calculating the hydrogen leakage rate Q is as follows:

[0086]

[0087] Where Q is the hydrogen leakage mass flow rate, or simply hydrogen leakage rate, in units of kg / s; A l The area of ​​the leakage hole is expressed in meters (m²). 2 P is the hydrogen pressure at the leak point, in Pa; C D is the correction factor for the hydrogen leakage rate at the leak hole, and its value ranges from 0.61 to 1.0; k is the hydrogen adiabatic coefficient, which is generally taken as 1.410 for hydrogen.

[0088] Specifically, step S4 includes:

[0089] Step S41: Calculate the leakage hole area based on the predicted nozzle orifice diameter; wherein the predicted nozzle orifice diameter is the leakage hole diameter.

[0090] Step S41: Based on the leakage hole area and the predicted gas pressure, the hydrogen leakage rate is calculated according to the hydrogen leakage rate calculation formula.

[0091] Step S5: Based on the hydrogen leakage rate over a period of time, use the Gaussian process regression algorithm to predict the relationship between the future hydrogen leakage rate Q and time t.

[0092] Specifically, step S4 includes:

[0093] Set a certain time step, obtain m different times t, and obtain the hydrogen leakage rate corresponding to time t through step S4, forming a vector D = {t} m Q m}, where D is the given training set, and the predicted value Q* at test time t* is calculated using the training set, denoted as Q*=f(t*). In the standard Gaussian process regression algorithm, Q... i and t i It is assumed that the function Q is satisfied. i =f(t) i ), i = 1, 2, ..., n. Consider f as a set of all t i The resulting joint Gaussian distribution. Let T = [t1, t2, ..., t n Q = [Q1, Q2, ..., Q] n ], Q*=[Q1*,Q2*,…,Q m This joint Gaussian distribution is represented as:

[0094]

[0095] Here, k(·,·) is the covariance function of the domain, k ** =k(t) * ,t * ), k t(i) =k(t) i ,t * ), K ll It is an n×n matrix, and the elements in the matrix are K. tt (i,j)=k(t i ,t j ), m(Q) is the mean of Q, and k is the kernel function.

[0096] This invention uses an exponential kernel function as the kernel function, and the form of the exponential kernel function is as follows:

[0097] k(t i,t j )=exp(-κ|t i -t j |);

[0098] Where κ is the scale parameter, t represents time, and t i and t j Indicates different times.

[0099] The predicted value can be obtained from the conditional probability formula. probability distribution f * .

[0100]

[0101] Therefore, -1 represents the inverse matrix and the predicted value at test position t*. The variance of the predicted value

[0102] In summary, based on the hydrogen leakage rate at different times within a certain period, the relationship between the future hydrogen leakage rate Q and time t can be predicted using the Gaussian process regression algorithm.

[0103] Step S6: Based on the predicted hydrogen leakage rate at different times, calculate the amount of hydrogen leakage during this period, and predict at which time in the future the amount of hydrogen leakage will reach the danger threshold, so as to achieve early warning of hydrogen leakage.

[0104] Specifically, based on the relationship between the hydrogen leakage rate Q and time t obtained in S5, the total amount of hydrogen leakage during the time period 0-t0 is... Assuming the set leakage threshold is Y0, the time t0 can be calculated, thus achieving early warning of hydrogen leakage.

[0105] This invention uses acoustic signals measured by an ultrasonic sensor to determine the hydrogen leakage rate and predict the amount of hydrogen leakage, thus enabling early warning of hydrogen leaks and improving the efficiency and accuracy of hydrogen leakage prediction.

[0106] Example 4

[0107] This invention provides an electronic device including a memory and a processor. The memory stores a computer program, and the processor runs the computer program to enable the electronic device to perform the hydrogen leakage rate measurement method based on an ultrasonic sensor according to Embodiment 1.

[0108] Alternatively, the aforementioned electronic device may be a server.

[0109] In addition, embodiments of the present invention also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the hydrogen leakage rate measurement method based on an ultrasonic sensor as described in Embodiment 1.

[0110] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0111] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for measuring hydrogen leakage rate based on an ultrasonic sensor, characterized in that, include: Based on an ultrasonic sensor array, the acoustic signal and signal phase difference corresponding to the target device are calculated; the target device is a device for storing hydrogen; multiple ultrasonic sensors are arranged around the target device to form an ultrasonic sensor array; the ultrasonic sensors are used to monitor the ultrasonic signals generated when hydrogen leaks; the acoustic signal corresponding to the target device is the sound pressure signal when the ultrasonic wave reaches the ultrasonic sensor; the signal phase difference corresponding to the target device is the signal phase difference when the ultrasonic wave reaches different ultrasonic sensors; The predicted nozzle aperture is obtained based on the acoustic signal, the signal phase difference, and the first conversion model determined by the deep learning algorithm. The predicted gas pressure is obtained based on the acoustic signal, the signal phase difference, and the second conversion model determined by a deep learning algorithm. Based on the predicted nozzle orifice diameter and the gas pressure, the hydrogen leakage rate at the target equipment leak point is calculated, specifically including: Calculate the leakage orifice area based on the predicted nozzle orifice diameter; where the predicted nozzle orifice diameter is the leakage orifice diameter. The hydrogen leakage rate is calculated based on the leakage hole area, the predicted gas pressure, and the hydrogen leakage rate calculation formula. The formula for calculating the hydrogen leakage rate is: In the formula, Q is the hydrogen leakage rate, with units of kg / s; A l The area of ​​the leakage hole is expressed in meters (m²). 2 P is the gas pressure at the leak point, in Pa; C D The correction factor for the hydrogen leakage rate at the leak hole; k is the hydrogen adiabatic coefficient, C D k is a constant.

2. The method for measuring hydrogen leakage rate based on an ultrasonic sensor according to claim 1, characterized in that, The calculation of the acoustic signal and signal phase difference corresponding to the target device based on the ultrasonic sensor array specifically includes: Based on ultrasonic sensor arrays and signal processing technology, the sound pressure signal when ultrasonic waves reach the ultrasonic sensor, as well as the signal phase difference when ultrasonic waves reach different ultrasonic sensors, are obtained.

3. The method for measuring hydrogen leakage rate based on an ultrasonic sensor according to claim 1, characterized in that, Also includes: Based on the hydrogen leakage rate at the target equipment leak point over a period of time, a Gaussian process regression algorithm is used to determine the relationship between the hydrogen leakage rate at the target equipment leak point and time in the future period.

4. The method for measuring hydrogen leakage rate based on an ultrasonic sensor according to claim 3, characterized in that, Also includes: Based on the relationship between the hydrogen leakage rate at the target equipment leak point and time in the future period, the hydrogen leakage amount at each moment corresponding to the leak point in the target equipment in the future period is calculated by integration.

5. The method for measuring hydrogen leakage rate based on an ultrasonic sensor according to claim 4, characterized in that, Also includes: In chronological order, the predicted hydrogen leakage amount at the target equipment leak point in future time periods is compared with the leakage threshold in turn; When the predicted hydrogen leakage amount at the target equipment leak point in the future time period exceeds the leakage threshold, the comparison is stopped, and the time corresponding to the predicted hydrogen leakage amount at the target equipment leak point in the future time period when the comparison is stopped is output along with a hydrogen leakage warning command.

6. A hydrogen leakage rate measurement system based on an ultrasonic sensor, characterized in that, include: An acoustic signal and signal phase difference calculation module is used to calculate the acoustic signal and signal phase difference corresponding to a target device based on an ultrasonic sensor array; the target device is a device for storing hydrogen. The nozzle aperture prediction module is used to obtain the predicted nozzle aperture based on the acoustic signal, the signal phase difference, and a first conversion model determined based on a deep learning algorithm; multiple ultrasonic sensors are arranged around the target device to form an ultrasonic sensor array; the ultrasonic sensors are used to monitor the ultrasonic signals generated when hydrogen leaks; the acoustic signal corresponding to the target device is the sound pressure signal when the ultrasonic wave reaches the ultrasonic sensor; the signal phase difference corresponding to the target device is the signal phase difference when the ultrasonic wave reaches different ultrasonic sensors; A gas pressure prediction module is used to obtain the predicted gas pressure based on the acoustic signal, the signal phase difference, and a second conversion model determined based on a deep learning algorithm. A hydrogen leakage rate prediction module is used to calculate the hydrogen leakage rate at the leak point of the target equipment based on the predicted nozzle orifice diameter and the gas pressure, specifically including: Calculate the leakage orifice area based on the predicted nozzle orifice diameter; where the predicted nozzle orifice diameter is the leakage orifice diameter. The hydrogen leakage rate is calculated based on the leakage hole area, the predicted gas pressure, and the hydrogen leakage rate calculation formula. The formula for calculating the hydrogen leakage rate is: In the formula, Q is the hydrogen leakage rate, with units of kg / s; A l The area of ​​the leakage hole is expressed in meters (m²). 2 P is the gas pressure at the leak point, in Pa; C D The correction factor for the hydrogen leakage rate at the leak hole; k is the hydrogen adiabatic coefficient, C D k is a constant.

7. A hydrogen leakage rate measurement system based on an ultrasonic sensor according to claim 6, characterized in that, Also includes: The relationship determination module is used to determine the relationship between the hydrogen leakage rate at the target equipment leak point and time in the future period based on the hydrogen leakage rate at the target equipment leak point over a period of time and using a Gaussian process regression algorithm. The hydrogen leakage prediction module is used to calculate the hydrogen leakage amount at each moment of the target equipment leakage point in the future period based on the relationship between the hydrogen leakage rate and time in the future period. The hydrogen leakage time prediction module is used to compare the predicted hydrogen leakage amount at the target equipment leakage point in the future time period with the leakage threshold in chronological order. When the predicted hydrogen leakage amount at the target equipment leakage point in the future time period is greater than the leakage threshold, the comparison stops, and the module outputs the time corresponding to the predicted hydrogen leakage amount at the target equipment leakage point in the future time period when the comparison stops, as well as a hydrogen leakage warning command.

8. An electronic device, characterized in that, The device includes a memory and a processor, the memory being used to store a computer program, and the processor running the computer program to cause the electronic device to perform the hydrogen leakage rate measurement method based on an ultrasonic sensor according to any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the hydrogen leakage rate measurement method based on an ultrasonic sensor as described in any one of claims 1 to 5.

Images