High-pressure gas pipeline leakage online monitoring method and system

Abstract

The invention discloses an online monitoring method and system for leakage of a high-pressure gas pipeline, and relates to the field of gas leakage detection.The method comprises the steps that a monitoring image is acquired; determining a displacement vector diagram based on the monitoring image and the reference image; the reference image is an image of the to-be-detected high-pressure gas pipeline when no leakage exists; obtaining a to-be-detected field area based on the monitoring image; the to-be-measured field area is a square area containing a jet flow cone; the jet cone is a conical area generated by leakage of the to-be-detected gas when the to-be-detected high-pressure gas pipeline has gas leakage; determining the refractive index of the to-be-measured field boundary of the to-be-measured field region; determining a density image of the to-be-measured field region according to the displacement vector diagram and the refractive index at the boundary of the to-be-measured field; on-line monitoring is performed on the density image of the to-be-measured field based on the convolutional neural network, and a monitoring result is obtained; the monitoring result comprises whether the to-be-detected high-pressure gas pipeline leaks or not. According to the invention, low-cost and high-sensitivity online leakage monitoring is realized.

Description

Technical Field

[0001] The present application relates to the technical field of gas leakage detection, and in particular to an online monitoring method and system for high-pressure gas pipeline leakage. Background Art

[0002] The operation of large-scale special electrical equipment involves the transportation and storage of various flammable gases and high-temperature and high-pressure gases through pipelines. Once a leak occurs, it will not only cause chemical pollution, but also cause explosion accidents in serious cases, endangering the personal safety of on-site workers and causing irreversible equipment damage. Therefore, online monitoring of high-pressure gas pipeline leaks is very necessary.

[0003] At present, the relevant gas leakage monitoring methods in industry include soap film method, fixed point catalytic combustion method, infrared thermal imaging method and Schlieren method, etc. However, it is difficult for the above technologies to achieve online monitoring of high-pressure gas pipeline leakage with both low cost and high sensitivity. Gas leakage is still a major safety hazard that endangers workers during the operation of large-scale special electrical equipment. Summary of the invention

[0004] The purpose of this application is to provide a method and system for online monitoring of high-pressure gas pipeline leakage, which can realize low-cost, high-sensitivity online leakage monitoring of high-pressure gas pipelines in large special electrical equipment.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for online monitoring of leakage in a high-pressure gas pipeline, comprising:

[0007] Acquire a monitoring image; the monitoring image is an image obtained by real-time shooting of the high-pressure gas pipeline to be tested;

[0008] Determine a displacement vector graph based on the monitoring image and a reference image; the reference image is an image of the high-pressure gas pipeline to be tested when no leakage exists;

[0009] A field area to be tested is obtained based on the monitoring image; the field area to be tested is a square area including a jet cone; the jet cone is a cone-shaped area generated by the leakage of the gas to be tested when there is a gas leak in the high-pressure gas pipeline to be tested;

[0010] Determine the refractive index at the boundary of the field to be measured in the field to be measured area;

[0011] Determine a density image of the area of ​​the field to be measured according to the displacement vector diagram and the refractive index at the boundary of the field to be measured;

[0012] Based on the convolutional neural network, the density image of the field area to be tested is monitored online to obtain a monitoring result; the monitoring result includes: whether there is a leak in the high-pressure gas pipeline to be tested.

[0013] Optionally, determining a displacement vector map based on the monitoring image and the reference image specifically includes:

[0014] Performing image enhancement on the monitoring image based on the superposition principle;

[0015] The enhanced monitoring image and the reference image are cross-correlated to obtain a displacement vector diagram; the displacement vector diagram is used to represent the position vector relationship of the same light on the monitoring image and the reference image.

[0016] Optionally, determining the refractive index at the boundary of the field to be measured of the field to be measured specifically includes:

[0017] Substituting the gas pressure and gas temperature in the high-pressure gas pipeline to be measured into the ideal gas state equation to calculate the gas density at the boundary of the field to be measured;

[0018] The gas density at the boundary of the field to be measured is substituted into the Gladstone-Dyer equation to calculate the refractive index at the boundary of the field to be measured.

[0019] Optionally, performing cross-correlation calculation on the enhanced monitoring image and the reference image to obtain a displacement vector map specifically includes:

[0020] Calibrate the enhanced monitoring image to obtain a calibrated monitoring image;

[0021] A query window is used to perform cross-correlation calculation on the calibrated monitoring image and the reference image to obtain a displacement vector diagram; the size of the query window is selected according to the different gas pressures in the high-pressure gas pipeline to be measured.

[0022] Optionally, determining a density image of the area of ​​the field to be measured according to the displacement vector image and a refractive index at a boundary of the field to be measured specifically includes:

[0023] Determine displacement vector data according to the displacement vector diagram; the displacement vector data includes: the displacement in the X direction and the Y direction of the difference between the position of the light emitted from the same position in the background after passing through the field area to be measured in the monitoring image and the initial position of the light emitted from the same position in the background in the reference image; the background is the focus position of the camera;

[0024] Substituting the refractive index at the boundary of the field to be measured and the displacement vector data into the Poisson equation, performing iterative solution to obtain the refractive index of the field to be measured;

[0025] The refractive index of the field to be measured is substituted into the Gladstone-Dyer equation to calculate and obtain a density image of the field to be measured.

[0026] Optionally, the calculation formula for the gas density at the boundary of the field to be measured is:

[0027]

[0028] Where ρ is the gas density at the boundary of the field to be measured, P is the gas pressure in the high-pressure gas pipeline to be measured, M is the molar mass obtained according to the type of gas in the high-pressure gas pipeline to be measured, and R g is the ideal gas constant, and T is the gas temperature in the high-pressure gas pipeline to be measured.

[0029] Optionally, the calculation formula for the refractive index at the boundary of the field to be measured is:

[0030] n0=kρ+1;

[0031] Among them, n0 is the refractive index at the boundary of the field to be measured, k is the Glaston-Dyer coefficient, and ρ is the gas density at the boundary of the field to be measured.

[0032] Optionally, the calculation formula for the refractive index of the field to be measured is:

[0033]

[0034] Where n is the refractive index of the field to be measured, n0 is the refractive index of the gas boundary to be measured at room temperature and pressure, W is the thickness of the field to be measured, and Z d is the distance between the field to be measured and the background, x is the coordinate of the initial position of the light emitted from the same position in the background in the reference image in the X direction, y is the coordinate of the initial position of the light emitted from the same position in the background in the reference image in the Y direction, Δ x is the displacement in the X direction of the difference between the position of the light emitted from the same position in the background after passing through the field to be measured in the monitoring image and the initial position of the same light emitted from the same position in the background in the reference image, Δ y It is the displacement in the Y direction of the difference between the position of the light emitted from the same position in the background after passing through the field to be measured in the monitoring image and the initial position of the light emitted from the same position in the background in the reference image.

[0035] Optionally, after the density image of the field area to be measured is monitored online based on a convolutional neural network and the monitoring result is obtained, the high-pressure gas pipeline leakage online monitoring method further includes:

[0036] Constructing a database; the database includes background schlieren measurement result data obtained in calibration experiments with different leakage diameters and pressures for gas types in an experimental high-pressure gas pipeline; the background schlieren measurement result data includes density distribution of the field area to be measured corresponding to the gas type in the experimental high-pressure gas pipeline when it leaks; the experimental high-pressure gas pipeline and the high-pressure gas pipeline to be measured are the same pipeline;

[0037] If the monitoring result is that there is a leak, the density distribution of the field area to be tested of the high-pressure gas pipeline to be tested is compared with the corresponding background schlieren measurement result data in the database to obtain similarity; the density distribution of the field area to be tested of the high-pressure gas pipeline to be tested is determined according to the density image of the field area to be tested;

[0038] When the similarity is greater than a set threshold, an alarm signal is issued.

[0039] In a second aspect, the present application provides an online monitoring system for leakage of a high-pressure gas pipeline, comprising: an imaging device and a computer;

[0040] The imaging device is arranged above the high-pressure gas pipeline to be tested; the imaging device is connected to the computer, and is used to take real-time photos of the high-pressure gas pipeline to be tested to obtain a monitoring image and send the monitoring image to the computer; the computer comprises: an image acquisition module, a displacement vector diagram determination module, a field area determination module to be tested, a refractive index determination module at the boundary of the field to be tested, a density image determination module and an online monitoring module;

[0041] An image acquisition module, used for acquiring the monitoring image;

[0042] A displacement vector diagram determining module, used to determine a displacement vector diagram based on the monitoring image and a reference image; the reference image is an image of the high-pressure gas pipeline to be tested when there is no leakage;

[0043] A module for determining a field area to be tested, used for obtaining a field area to be tested based on the monitoring image; the field area to be tested is a square area including a jet cone; the jet cone is a cone-shaped area generated by the leakage of the gas to be tested when there is a gas leak in the high-pressure gas pipeline to be tested;

[0044] A module for determining the refractive index at the boundary of the field to be measured, used to determine the refractive index at the boundary of the field to be measured in the field to be measured area;

[0045] A density image determination module, used to determine the density image of the field to be measured according to the displacement vector diagram and the refractive index at the boundary of the field to be measured;

[0046] The online monitoring module is used to perform online monitoring of the density image of the field to be tested based on a convolutional neural network to obtain monitoring results; the monitoring results include: whether there is a leak in the high-pressure gas pipeline to be tested.

[0047] According to the specific embodiments provided in this application, this application has the following technical effects:

[0048] The present application provides a method and system for online monitoring of leakage in a high-pressure gas pipeline, which determines a displacement vector based on a monitoring image and a reference image; obtains a field area to be tested based on the monitoring image and determines the refractive index at the boundary of the field area to be tested; determines a density image of the field area to be tested based on the displacement vector and the refractive index at the boundary of the field area to be tested; and performs online monitoring of the density image of the field area to be tested based on a convolutional neural network to obtain a monitoring result. The present application abandons the lens group and the complex optical path, and obtains a density image of the field area to be tested through the above scheme, thereby achieving less equipment, lower environmental requirements and a larger field of view, and by determining the density image of the field area to be tested and the real-time and efficient recognition of the convolutional neural network, it can realize online monitoring of high-pressure gas leakage, improve the monitoring sensitivity, and thus realize low-cost, high-sensitivity online leakage monitoring of high-pressure gas pipelines in large special electrical equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 This is a flow chart of an online monitoring method for high-pressure gas pipeline leakage in one embodiment of the present application;

[0051] Figure 2 A schematic diagram of a natural background texture light path provided in an embodiment of the present application;

[0052] Figure 3 A schematic diagram of the overall layout simulation of a high-pressure gas pipeline leakage online monitoring system provided in one embodiment of the present application;

[0053] Figure 4 A monitoring schematic diagram of an online monitoring system for high-pressure gas pipeline leakage provided in an embodiment of the present application;

[0054] Figure 5 A schematic diagram of an image formed in an imaging device provided in an embodiment of the present application;

[0055] Figure 6A schematic diagram of the arrangement of an imaging device in an embodiment of the present application;

[0056] Figure 7 This is a schematic diagram of functional modules of an online monitoring system for leakage of a high-pressure gas pipeline in one embodiment of the present application;

[0057] Figure 8 A schematic diagram of the installation and monitoring steps of a high-pressure gas pipeline monitoring system for a steam turbine provided in one embodiment of the present application;

[0058] Fig. 9 A partial leakage schematic diagram of the obtained leakage displacement vector diagram provided in an embodiment of the present application;

[0059] Fig.10 for Fig. 9 Schematic diagram of the corresponding leakage field image structure division.

[0060] Figure numerals: 1 - imaging device, 2 - light source, 3 - high-pressure gas pipeline to be tested, 4 - computer, 5 - alarm device. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0062] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0063] Among the relevant gas leakage monitoring methods, the soap film method is to apply soapy water to the surface of the pipeline to be tested, and determine whether a leak occurs by observing whether bubbles appear. Although it has the lowest cost, it consumes a lot of manpower and cannot be applied to the detection of high-pressure gas leaks; the fixed-point catalytic combustion method is to place a detection device at a fixed point to perform continuous catalytic combustion on the gas in the air to determine whether there is a leak of flammable gas. It has a low cost but cannot quickly locate the leak point and requires the leak of the flammable gas to reach a certain scale before it can be detected; the infrared thermal imaging method uses the infrared absorption characteristics of the gas for detection. It is more sensitive but has a higher cost and is difficult to apply to situations where high-pressure air or water vapor leaks into a relatively open air domain; the Schlieren method uses the density gradient of the leaking gas and the surrounding air environment for detection. It can perform high-resolution real-time imaging of the leakage field, but the imaging window is limited by the size of the optical device and the optical path is complex and precise, making it difficult to promote on a large scale in industrial production practice. Therefore, in order to eliminate the safety hazards caused by high-pressure pipeline gas leakage during the operation of large-scale special electrical equipment, the present application provides a high-pressure gas pipeline leakage online monitoring method and system, which can realize low-cost, high-sensitivity online leakage monitoring of high-pressure gas pipelines in large-scale special electrical equipment.

[0064] In an exemplary embodiment, Figure 1 As shown, a method for online monitoring of leakage in a high-pressure gas pipeline is provided, comprising the following S1 to S6. Among them:

[0065] S1: Acquire a monitoring image; the monitoring image is an image obtained by real-time shooting of the high-pressure gas pipeline to be tested; the pressure in the high-pressure gas pipeline to be tested is above 1Mpa. As an optional implementation, the monitoring image uses a non-tested high-pressure gas pipeline in the high-pressure gas pipeline group located at the camera focus position as the background, and uses the natural background schlieren method to obtain an image by real-time shooting of the high-pressure gas pipeline to be tested; the high-pressure gas pipeline group includes multiple high-pressure gas pipelines. During the monitoring process, the entire high-pressure gas pipeline group is divided into two parts according to the spatial distribution, and each part has an imaging device on one side. When the first part is used as the high-pressure gas pipeline to be tested, the first imaging device is used for shooting, and the second part is used as the background; when the second part is used as the high-pressure gas pipeline to be tested, the second imaging device is used for shooting, and the first part is used as the background; thereby, the entire pipeline group is monitored through the complementarity of the two imaging devices.

[0066] S2: Determine a displacement vector map based on the monitoring image and the reference image; the reference image is an image of the high-pressure gas pipeline to be tested when there is no leakage. As an optional implementation, the reference image is an image of the high-pressure gas pipeline to be tested when there is no leakage obtained by using a natural background schlieren method.

[0067] S3: obtaining a field area to be tested based on the monitoring image; the field area to be tested is a square area including a jet cone; the jet cone is a conical area generated by the leakage of the high-pressure gas to be tested when there is a gas leak in the high-pressure gas pipeline to be tested.

[0068] S4: Determine the refractive index at the boundary of the field to be measured in the field to be measured area.

[0069] S5: Determine a density image of the area of ​​the field to be measured according to the displacement vector image and the refractive index at the boundary of the field to be measured.

[0070] S6: Perform online monitoring of the density image of the field area to be tested based on a convolutional neural network to obtain a monitoring result; the monitoring result includes: whether there is a leak in the high-pressure gas pipeline to be tested.

[0071] In another exemplary embodiment of the present application, step S2 specifically includes:

[0072] S21: Enhance the monitoring image based on the superposition principle. Specifically, S211, the monitoring images are grouped in time sequence. According to the different gas pressures in the high-pressure gas pipeline to be tested, the images can be divided into a group of 10-100 images. The higher the gas pressure in the pipeline, the smaller the capacity of the selected group should be. This part is to superimpose the images in the group to obtain the effect of denoising and enhancing the resolution. S212, after superimposing all the images contained in each group, the average value is taken to obtain a super-resolution image.

[0073] S22: performing cross-correlation calculation on the enhanced monitoring image (super-resolution image) and the reference image to obtain a displacement vector map.

[0074] In another exemplary embodiment of the present application, the refractive index at the boundary of the field to be measured is obtained according to the atmospheric refractive index and the pipeline gas pressure, and S4 specifically includes:

[0075] S41: Substituting the gas pressure and gas temperature in the high-pressure gas pipeline to be measured into the ideal gas state equation to calculate the gas density at the boundary of the field to be measured.

[0076] S42: Substituting the gas density at the boundary of the field to be measured into the Gladstone-Dyer equation, and calculating the refractive index at the boundary of the field to be measured.

[0077] In another exemplary embodiment of the present application, S22 specifically includes:

[0078] S221: Calibrate the enhanced monitoring image to obtain a calibrated monitoring image, wherein calibration refers to adding a coordinate ruler to the image using an object of a specific known size in the image (such as the diameter of the pipeline to be measured) to facilitate subsequent calculations.

[0079] S222: After calibrating the obtained super-resolution image, perform cross-correlation calculation on it and the reference image taken previously. Specifically, a query window is used to perform cross-correlation calculation on the calibrated monitoring image and the reference image to obtain a displacement vector map; the size of the query window is selected according to the different gas pressures in the high-pressure gas pipeline to be tested. The gas pressure in the transportation pipeline in the power plant is generally known and unchanged. If the high-pressure pipeline is monitored, a smaller query window is selected. The higher the gas pressure in the pipeline, the larger the selected query window should be, and finally the displacement vector map is calculated. The displacement vector map is the position vector relationship of the same light on the monitoring image and the reference image. After the light passes through the inhomogeneous density field, it will be deflected, and the position of the deflected light reaching the camera imaging surface, that is, the monitoring image, will deviate from the position when the inhomogeneous density field does not exist, that is, the reference image. The displacement vector refers to the position vector relationship of the same light on the two.

[0080] In another exemplary embodiment of the present application, the refractive index at the location of the pipeline leakage port is difficult to measure or estimate, so the density is calculated by the type, pressure and temperature of the flowing gas in the pipeline, and then the Glastondale formula is used to calculate the refractive index at the corresponding location of the pipeline leakage port. The refractive index of the remaining boundary parts can be regarded as the ambient gas refractive index when a larger query window is taken. After the obtained displacement vector diagram is input with the refractive index at the boundary of the field to be measured according to the high-pressure pipeline pressure, an inversion calculation is performed to obtain the density image of the field to be measured. S5 specifically includes:

[0081] S51: Determine displacement vector data according to the displacement vector diagram; the displacement vector data includes: the displacement in the X direction and the Y direction of the difference between the position of the light emitted from the same position in the background after passing through the field area to be tested in the monitoring image and the initial position of the light emitted from the same position in the background in the reference image; the background is the camera focus position. Specifically, the camera focus position is the non-tested high-pressure gas pipeline in the high-pressure gas pipeline group.

[0082] S52: Substitute the refractive index at the boundary of the field to be measured and the displacement vector data into the Poisson equation, and perform iterative solution to obtain the refractive index of the field to be measured.

[0083] S53: Substituting the refractive index of the field to be measured into the Gladstone-Dyer equation to calculate and obtain a density image of the field to be measured.

[0084] In another exemplary embodiment of the present application, the calculation formula of the gas density at the boundary of the field to be measured is:

[0085]

[0086] Where ρ is the gas density at the boundary of the field to be measured, P is the gas pressure in the high-pressure gas pipeline to be measured, M is the molar mass obtained according to the type of gas in the high-pressure gas pipeline to be measured, and R g is the ideal gas constant, and T is the gas temperature in the high-pressure gas pipeline to be measured.

[0087] In another exemplary embodiment of the present application, the calculation formula of the refractive index at the boundary of the field to be measured is:

[0088] n0=kρ+1.

[0089] Among them, n0 is the refractive index at the boundary of the field to be measured, k is the Glaston-Dyer coefficient, and ρ is the gas density at the boundary of the field to be measured.

[0090] In another exemplary embodiment of the present application, the calculation formula of the refractive index of the field to be measured is:

[0091]

[0092] Where n is the refractive index of the field to be measured, n0 is the refractive index of the gas boundary to be measured at room temperature and pressure, W is the thickness of the field to be measured, which is usually ignored in the actual calculation process, and Z d is the distance between the field to be measured and the background, x is the coordinate of the initial position of the light emitted from the same position in the background in the reference image in the X direction, y is the coordinate of the initial position of the light emitted from the same position in the background in the reference image in the Y direction, Δ x is the displacement in the X direction of the difference between the position of the light emitted from the same position in the background after passing through the field to be measured in the monitoring image and the initial position of the light emitted from the same position in the background in the reference image, Δ y It is the displacement in the Y direction of the difference between the position of the light emitted from the same position in the background after passing through the field to be measured in the monitoring image and the initial position of the light emitted from the same position in the background in the reference image.

[0093] In another exemplary embodiment of the present application, after S6, the high-pressure gas pipeline leakage online monitoring method further includes:

[0094] S61: Construct a database; the database includes background schlieren measurement result data obtained in a calibration experiment with different leakage calibers and pressures for the gas type of the experimental high-pressure gas pipeline; the background schlieren measurement result data includes the density distribution of the field area to be tested corresponding to the gas type of the experimental high-pressure gas pipeline leaking; the experimental high-pressure gas pipeline and the high-pressure gas pipeline to be tested are the same pipeline; specifically, the gas type, pipeline caliber and gas pressure of the experimental high-pressure gas pipeline and the high-pressure gas pipeline to be tested are the same.

[0095] S62: If the monitoring result shows that there is a leak, the density distribution of the test field area of ​​the high-pressure gas pipeline to be tested is compared with the corresponding background schlieren measurement result data in the database to obtain similarity; the density distribution of the test field area of ​​the high-pressure gas pipeline to be tested is determined based on the density image of the test field area.

[0096] S63: When the similarity is greater than the set threshold, an alarm signal is issued. The threshold is set according to the leakage hazard level, and the leakage caliber and leakage pressure are output according to the leakage image. The reference image, monitoring image and leakage image are all images of the same pipeline obtained by the same imaging device under different conditions: the reference image is an image obtained during the equipment debugging phase when it is confirmed that there is no leakage; the monitoring image is an image obtained during the operation of the equipment. Under normal circumstances, there is no leakage, so the light is not deflected by the cone area generated by the high-pressure gas leakage, that is, its displacement vector field is zero displacement; the leakage image is during the monitoring process, when a high-pressure gas leak occurs, and a cone area appears in the displacement vector field, after which inversion calculation and neural network judgment are performed.

[0097] In another exemplary embodiment of the present application, S6 specifically includes:

[0098] The density images (field cloud images) of experimental high-pressure gas pipeline leakage with known leakage pressure and corresponding gas types of different calibers in the database are input into the convolutional neural network for learning. The convolutional neural network continuously performs image recognition and comparison on the density images of the field area to be tested obtained in S5 to obtain the monitoring results.

[0099] like Figure 2 As shown, the present application uses the background high-pressure gas pipeline as the background pattern, and adopts the natural background Schlieren method to obtain the monitoring image and the reference image. Based on the Schlieren technology, the background Schlieren technology is developed on the basis of the Schlieren method, specifically using a plane light source and random scattered points as the background plate to detect the density field of the leaked gas and the surrounding air environment. The natural background Schlieren method of the present application is a new optical measurement technology proposed based on the background Schlieren method. It has the same principle as the Schlieren method. Both are based on the density gradient of the field to be measured and the surrounding environment for imaging and detection, but different from the background Schlieren method, the natural background method uses a natural background with a certain contrast to replace the traditional background composed of a plane light source and random scattered points. The present application uses the background high-pressure gas pipeline as the natural background, abandons the production and arrangement of the luminous background plate, breaks through the limitation of the production and arrangement of the luminous background plate on the size of the field of view, and further reduces the monitoring cost.

[0100] Based on the near optical axis assumption: the deflection angle of the light relative to the main optical axis is extremely small, that is, the magnitude of the light deflection angle is approximately equal to the magnitude of its own tangent value, and it is assumed that the thickness W of the field to be tested can be ignored relative to the distance between it and the background. Finally, the relationship between the light deflection angle ε and the displacement Δ after the light passes through the field to be tested with uneven density is obtained:

[0101]

[0102] In the formula, ε x is the deflection angle of the light in the X direction after passing through the field to be measured, ε y It is the deflection angle in the Y direction after the light passes through the field to be measured.

[0103] Z D is the distance from the field to be measured to the background, Z A Z is the distance from the lens group in the camera (imaging device) to the high-pressure gas pipeline group to be tested. B is the distance from the lens group in the camera (imaging device) to the background, Z B The value is Z D Value and Z A The sum of the values, Z i It is the distance from the lens group to the photosensitive device in the camera (imaging device). x is the displacement in the X direction (not shown) of the difference between the position of the light emitted from the same position in the background after passing through the field to be measured in the monitoring image and the initial position of the light emitted from the same position in the background in the reference image, Δ y is the displacement in the Y direction of the difference between the position of the light emitted from the same position in the background after passing through the field to be measured in the monitoring image and the initial position of the light emitted from the same position in the background in the reference image; Δ y ′ is the displacement of the light in the Y direction relative to the initial position on the background after the light passes through the test field area. The above parameters can be directly obtained by calibrating the (two-dimensional) displacement vector diagram to obtain the relationship between the displacement Δ after the light passes through the test field area with uneven density.

[0104] This application adopts the natural background schlieren method to obtain displacement vector data, discards the lens group and complex optical path, thereby obtaining less equipment, lower environmental requirements and a larger field of view. By performing uninterrupted cross-correlation calculations between the monitoring image and the set reference image and real-time and efficient recognition of the convolutional neural network, online monitoring of high-pressure gas leaks can be achieved.

[0105] Based on the same inventive concept, the embodiment of the present application also provides a high-pressure gas pipeline leakage online monitoring system for implementing the high-pressure gas pipeline leakage online monitoring method involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more high-pressure gas pipeline leakage online monitoring system embodiments provided below can refer to the limitations of the high-pressure gas pipeline leakage online monitoring method above, and will not be repeated here.

[0106] In an exemplary embodiment, a high-pressure gas pipeline leakage online monitoring system is provided, including hardware equipment: imaging equipment, computer; the software part of the computer: image enhancement algorithm, cross-correlation algorithm, convolutional neural network algorithm. The specific scheme is as follows:

[0107] like Figure 3 and Figure 4 As shown, the high-pressure gas pipeline leakage online monitoring system includes: an imaging device 1 and a computer 4; the imaging device 1 is arranged above the high-pressure gas pipeline 3 to be tested, so that the pipeline in the high-pressure gas pipeline 3 to be tested in the captured image is as free of overlap or cover as possible; the image formed in the imaging device 1 should be as shown in FIG. Figure 5 As shown, the imaging device 1 is connected to the computer 4, and the imaging device 1 is used to take real-time photos of the high-pressure gas pipeline 3 to be tested to obtain a monitoring image and send the monitoring image to the computer 4. The imaging device 1 is preferably an industrial CCD camera or an industrial camera with equivalent high spatial and temporal resolution.

[0108] like Figure 6 As shown, in actual application, the natural background schlieren method uses an imaging device to focus on a background pattern of a background high-pressure gas pipeline, and the field area to be tested is located between the imaging device and the background pattern. Multiple high-pressure gas pipelines form a high-pressure gas pipeline group, and imaging devices are placed on both sides of the high-pressure gas pipeline group. At the same time, the entire high-pressure gas pipeline group is divided into two parts according to the spatial distribution. Taking the operation of the first imaging device as an example, at this time, the left half of the pipeline is the first high-pressure gas pipeline group to be tested, and the right half of the pipeline is the first background high-pressure gas pipeline group, which is used as the background pattern of the first imaging device. The first imaging device focuses on the first background high-pressure gas pipeline group in the right half, and monitors the first high-pressure gas pipeline group to be tested in the left half; conversely, the second imaging device works in the same way. Figure 6 The right half of the pipeline serves as the second high-pressure gas pipeline group to be tested by the second imaging device, and the left half of the pipeline serves as the second background high-pressure gas pipeline group, which is used as the background pattern of the second imaging device. The two imaging devices work simultaneously to achieve real-time monitoring of the entire high-pressure gas pipeline group to be tested.

[0109] like Figure 7As shown, the computer 4 includes: an image acquisition module, a displacement vector map determination module, a test field area determination module, a test field boundary refractive index determination module, a density image determination module and an online monitoring module.

[0110] An image acquisition module is used to acquire the monitoring image.

[0111] The displacement vector diagram determining module is used to determine the displacement vector diagram based on the monitoring image and the reference image; the reference image is an image of the high-pressure gas pipeline to be tested when there is no leakage.

[0112] The module for determining the field area to be tested is used to obtain the field area to be tested based on the monitoring image; the field area to be tested is a square area containing a jet cone; the jet cone is a conical area produced by the leakage of the high-pressure gas to be tested when there is a gas leak in the high-pressure gas pipeline to be tested.

[0113] The module for determining the refractive index at the boundary of the field to be measured is used to determine the refractive index at the boundary of the field to be measured of the field to be measured area.

[0114] The density image determination module is used to determine the density image of the area of ​​the field to be measured according to the displacement vector map and the refractive index at the boundary of the field to be measured.

[0115] The online monitoring module is used to perform online monitoring of the density image of the field to be tested based on a convolutional neural network to obtain monitoring results; the monitoring results include: whether there is a leak in the high-pressure gas pipeline to be tested.

[0116] In another exemplary embodiment of the present application, the high-pressure gas pipeline leakage online monitoring system also includes an alarm device and a light source; the alarm device is connected to the computer, and the alarm device is used to receive an alarm signal sent by the computer and to issue an alarm; the light source is arranged above the high-pressure gas pipeline to be tested, so that the high-pressure gas pipeline to be tested in the shooting field of view can be evenly illuminated by this light source, and the light source can use an industrial LED light source and keep the industrial LED turned on.

[0117] During the operation of the system, the computer receives the monitoring image from the imaging device in real time and performs image enhancement based on the superposition principle, and performs cross-correlation calculation on the enhanced super-resolution image and the reference image to obtain a displacement vector map. The refractive index at the boundary of the field to be measured is input into the displacement vector map to perform an inversion calculation to obtain the density distribution of the field to be measured. Finally, the density image of the obtained field to be measured is monitored online based on the convolutional neural network, and when the similarity exceeds ninety percent, a signal is sent to the alarm device for alarm. The present application can realize low-cost and high-sensitivity online monitoring of high-pressure pipeline leakage.

[0118] In the actual production process of natural gas power plants, the transportation of various high-pressure gases such as blast furnace gas, high-pressure oxygen, high-pressure air, high-pressure steam, high-pressure nitrogen and high-pressure argon is involved. Therefore, the following will take the power plant as an example to explain the implementation method of this application. The system installation and monitoring steps are as follows: Figure 8 shown.

[0119] The specific layout of a single device is explained by taking the online monitoring of the high-pressure gas pipeline of the steam turbine, which is a typical high-temperature and high-pressure gas pipeline transportation link in the power plant production process, as an example. First, the monitoring system is assembled according to the system simulation structure. The specific setting requirements are as follows:

[0120] The high-pressure gas pipeline 3 to be tested is a high-pressure gas pipeline of a steam turbine. The imaging device 1 is a high-speed camera installed at a designated position above the steam turbine pipeline. It is required to ensure that there is no overlap or cover in the pipeline of the high-pressure gas pipeline to be tested in the captured image.

[0121] Light source 2 is an industrial LED, which is installed near the installed imaging device and is constantly adjusted so that the high-pressure gas pipeline in the shooting field can be evenly illuminated by the light source. After that, the industrial LED is kept turned on and after confirming that there is no leakage in all pipelines in the steam turbine high-pressure gas pipeline, the image is taken by the imaging device 1 and transmitted to the computer 4 as a reference image. At this point, the system preparation work is completed, and the system can be arranged above multiple high-pressure gas pipelines and summarized on the console to realize online monitoring of high-pressure gas pipeline leakage in the production process of the entire plant.

[0122] During normal operation of the system, the computer 4 groups the monitoring images transmitted by the installed imaging device 1 in chronological order. Since the pressure of the steam turbine pipeline is usually 15 MPa or above, the images are divided into groups of 10. After superimposing all the images contained in each group, the average value is taken to obtain a super-resolution image.

[0123] After that, the obtained super-resolution image is calibrated and then cross-correlated with the previously taken reference image. Also, because the steam turbine pipeline pressure is usually 15 MPa or above, the query window size is 64x64 mm, and the displacement vector diagram is finally calculated.

[0124] By bringing the steam pressure and temperature in the high-pressure gas pipeline of the steam turbine into the ideal gas state equation, the gas density at the boundary of the field to be measured can be calculated:

[0125]

[0126] Among them, ρ is the gas density at the boundary of the field to be measured, M is the molar mass of water vapor, and R g is the ideal gas constant and T is the steam temperature.

[0127] After obtaining the gas density at the boundary of the field to be measured, it is substituted into the Glaston-Dyer equation to calculate the refractive index at the boundary of the field to be measured:

[0128] n0=kρ+1.

[0129] Among them, n0 is the refractive index at the boundary of the field to be measured, and k is the Gladstone-Dyer coefficient corresponding to water vapor.

[0130] Substitute the calculated refractive index at the boundary of the field to be measured into the Poisson equation, and the Poisson equation obtained by combining them is as follows:

[0131]

[0132] Wherein, n0 is the refractive index at the boundary of the field to be measured, that is, the refractive index of water vapor at the boundary of the field to be measured.

[0133] The above Poisson's equation is iteratively solved to obtain the refractive index of the field to be measured, and then the density image of the field to be measured can be obtained through the Gladstone-Dyer equation.

[0134] A convolutional neural network that has been trained on the leakage density images (i.e., density field cloud images) of high-pressure gas pipelines of different calibers with known leakage pressures and gas types is used to continuously perform image recognition and comparison on the density images of the field area to be tested obtained in the previous step. The risk factor of leakage of the steam turbine high-pressure gas pipeline is too high, so the threshold is set to 75%. Once the threshold is exceeded, the computer 4 outputs a signal to the alarm device 5 to alarm, such as Fig. 9 As shown in the figure, the green area of ​​the leakage site is composed of green arrows, which are displacement vectors obtained by cross-correlation calculation. The conical boundary on the left side of the high-pressure gas pipeline leakage in the steam turbine is the leakage boundary. Fig. 9 The circular structure surrounded by the green area is the Mach ring structure, such as Fig.10 As shown, the unit of the horizontal and vertical coordinates is pixel, the leakage field is the jet cone angle, the leakage diameter is 8mm, and the leakage pressure is 1Mpa.

[0135] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0136] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for online monitoring of high-pressure gas pipeline leakage, characterized in that: The online monitoring method for high-pressure gas pipeline leakage comprises: Acquire a monitoring image; the monitoring image is an image obtained by real-time shooting of the high-pressure gas pipeline to be tested; Determine a displacement vector graph based on the monitoring image and a reference image; the reference image is an image of the high-pressure gas pipeline to be tested when no leakage exists; A field area to be tested is obtained based on the monitoring image; the field area to be tested is a square area including a jet cone; the jet cone is a cone-shaped area generated by the leakage of the gas to be tested when there is a gas leak in the high-pressure gas pipeline to be tested; Determine the refractive index at the boundary of the field to be measured in the field to be measured area; Determine a density image of the area of ​​the field to be measured according to the displacement vector diagram and the refractive index at the boundary of the field to be measured; Based on the convolutional neural network, the density image of the field area to be tested is monitored online to obtain a monitoring result; the monitoring result includes: whether there is a leak in the high-pressure gas pipeline to be tested.

2. The method for online monitoring of high-pressure gas pipeline leakage according to claim 1, characterized in that: Determining a displacement vector map based on the monitoring image and the reference image specifically includes: Performing image enhancement on the monitoring image based on the superposition principle; The enhanced monitoring image and the reference image are cross-correlated to obtain a displacement vector diagram; the displacement vector diagram is used to represent the position vector relationship of the same light on the monitoring image and the reference image.

3. The method for online monitoring of high-pressure gas pipeline leakage according to claim 1, characterized in that: Determining the refractive index at the boundary of the field to be measured in the field to be measured region specifically includes: Substituting the gas pressure and gas temperature in the high-pressure gas pipeline to be measured into the ideal gas state equation to calculate the gas density at the boundary of the field to be measured; The gas density at the boundary of the field to be measured is substituted into the Gladstone-Dyer equation to calculate the refractive index at the boundary of the field to be measured.

4. The method for online monitoring of high-pressure gas pipeline leakage according to claim 2, characterized in that: The enhanced monitoring image and the reference image are cross-correlated to obtain a displacement vector map, which specifically includes: Calibrate the enhanced monitoring image to obtain a calibrated monitoring image; A query window is used to perform cross-correlation calculation on the calibrated monitoring image and the reference image to obtain a displacement vector diagram; the size of the query window is selected according to the different gas pressures in the high-pressure gas pipeline to be measured.

5. The method for online monitoring of high-pressure gas pipeline leakage according to claim 1, characterized in that: Determining a density image of the area of ​​the field to be measured according to the displacement vector diagram and the refractive index at the boundary of the field to be measured specifically includes: Determine displacement vector data according to the displacement vector diagram; the displacement vector data includes: the displacement in the X direction and the Y direction of the difference between the position of the light emitted from the same position in the background after passing through the field area to be measured in the monitoring image and the initial position of the light emitted from the same position in the background in the reference image; the background is the focus position of the camera; Substituting the refractive index at the boundary of the field to be measured and the displacement vector data into the Poisson equation, performing iterative solution to obtain the refractive index of the field to be measured; The refractive index of the field to be measured is substituted into the Gladstone-Dyer equation to calculate and obtain a density image of the field to be measured.

6. The method for online monitoring of high-pressure gas pipeline leakage according to claim 3, characterized in that: The calculation formula of the gas density at the boundary of the field to be measured is: Among them, ρ is the gas density at the boundary of the field to be measured, P is the gas pressure in the high-pressure gas pipeline to be measured, M is the molar mass obtained according to the type of gas in the high-pressure gas pipeline to be measured, and R g is the ideal gas constant, and T is the gas temperature in the high-pressure gas pipeline to be measured.

7. The method for online monitoring of high-pressure gas pipeline leakage according to claim 3, characterized in that: The calculation formula of the refractive index at the boundary of the field to be measured is: n0=kρ+1; Among them, n0 is the refractive index at the boundary of the field to be measured, k is the Glaston-Dyer coefficient, and ρ is the gas density at the boundary of the field to be measured.

8. The method for online monitoring of high-pressure gas pipeline leakage according to claim 5, characterized in that: The calculation formula of the refractive index of the field to be measured is: Where n is the refractive index of the field to be measured, n0 is the refractive index of the gas boundary to be measured at room temperature and pressure, W is the thickness of the field to be measured, and Z d is the distance between the field to be measured and the background, x is the coordinate of the initial position of the light emitted from the same position in the background in the reference image in the X direction, y is the coordinate of the initial position of the light emitted from the same position in the background in the reference image in the Y direction, Δ x is the displacement in the X direction of the difference between the position of the light emitted from the same position in the background after passing through the field to be measured in the monitoring image and the initial position of the light emitted from the same position in the background in the reference image, Δ y It is the displacement in the Y direction of the difference between the position of the light emitted from the same position in the background after passing through the field to be measured in the monitoring image and the initial position of the light emitted from the same position in the background in the reference image.

9. The method for online monitoring of high-pressure gas pipeline leakage according to claim 1, characterized in that: After performing online monitoring of the density image of the field area to be tested based on a convolutional neural network and obtaining the monitoring result, the online monitoring method for high-pressure gas pipeline leakage further includes: Constructing a database; the database includes background schlieren measurement result data obtained in calibration experiments with different leakage diameters and pressures for gas types in an experimental high-pressure gas pipeline; the background schlieren measurement result data includes density distribution of the field area to be measured corresponding to the gas type in the experimental high-pressure gas pipeline when it leaks; the experimental high-pressure gas pipeline and the high-pressure gas pipeline to be measured are the same pipeline; If the monitoring result is that there is a leak, the density distribution of the field area to be tested of the high-pressure gas pipeline to be tested is compared with the corresponding background schlieren measurement result data in the database to obtain similarity; the density distribution of the field area to be tested of the high-pressure gas pipeline to be tested is determined according to the density image of the field area to be tested; When the similarity is greater than a set threshold, an alarm signal is issued.

10. A high-pressure gas pipeline leakage online monitoring system, characterized in that: The high-pressure gas pipeline leakage online monitoring system comprises: an imaging device and a computer; The imaging device is arranged above the high-pressure gas pipeline to be tested; the imaging device is connected to the computer, and is used to take real-time photos of the high-pressure gas pipeline to be tested to obtain a monitoring image and send the monitoring image to the computer; the computer comprises: an image acquisition module, a displacement vector diagram determination module, a field area determination module to be tested, a refractive index determination module at the boundary of the field to be tested, a density image determination module and an online monitoring module; An image acquisition module, used for acquiring the monitoring image; A displacement vector diagram determining module, used to determine a displacement vector diagram based on the monitoring image and a reference image; the reference image is an image of the high-pressure gas pipeline to be tested when there is no leakage; A module for determining a field area to be tested, used for obtaining a field area to be tested based on the monitoring image; the field area to be tested is a square area including a jet cone, and the jet cone is a cone-shaped area generated by the leakage of the gas to be tested when there is a gas leak in the high-pressure gas pipeline to be tested; A module for determining the refractive index at the boundary of the field to be measured, used to determine the refractive index at the boundary of the field to be measured in the field to be measured area; A density image determination module, used to determine the density image of the field to be measured according to the displacement vector diagram and the refractive index at the boundary of the field to be measured; The online monitoring module is used to perform online monitoring of the density image of the field to be tested based on a convolutional neural network to obtain monitoring results; the monitoring results include: whether there is a leak in the high-pressure gas pipeline to be tested.

Images