Method, device and electronic device for measuring compressed air leakage and jet distance

Abstract

The application discloses a method and device for measuring compressed air leakage and jet distance, and electronic equipment, and relates to the technical field of air detection, comprising: acquiring an original schlieren image of a flow field of a to-be-detected pipeline by using a schlieren imaging system, and synchronously acquiring temperature and pressure parameters of the environment and the inside of the pipeline; processing the image by an AI feature extraction algorithm, identifying a leakage airflow form and classifying, and calculating a two-dimensional deflection angle distribution of the flow field; reconstructing a three-dimensional density field based on the two-dimensional deflection angle distribution, and calculating a leakage gas mass flow in combination with an analyzed two-dimensional velocity field; measuring and calculating an effective jet distance in combination with a high-speed compressible jet theory; and mapping the leakage related data to a visual display of a three-dimensional digital model of the pipeline. The compressed air leakage non-contact, high anti-interference visual detection is realized, the leakage amount and the jet distance can be quantified synchronously and accurately, the influence range of the leakage can be intuitively presented, and the precision, robustness and operation safety of the high-temperature and high-pressure pipeline leakage detection are improved.

Description

Technical Field

[0001] This application relates to the field of air detection technology, and in particular to a method, apparatus, and electronic device for measuring compressed air leakage and injection distance. Background Technology

[0002] In industrial settings, high-temperature, high-pressure compressed air leaks are highly concealed and pose significant safety risks. Related detection technologies have significant limitations: traditional ultrasonic testing is susceptible to interference from strong background noise, leading to missed or false alarms and making it impossible to accurately estimate leak flow rates; infrared thermal imaging is affected by strong thermal background radiation, making it difficult to capture the shape of transparent gas jets and thus unable to quantitatively measure flow velocity and flow rate; soap solution methods and contact flowmeters pose extremely high safety risks under high-temperature, high-pressure conditions, making non-contact detection of the entire pipeline network impossible. Furthermore, most of these technologies can only qualitatively detect leaks, failing to simultaneously and accurately quantify the leak's mass flow rate and effective jet distance, thus hindering a comprehensive quantitative assessment of the energy loss and safety risks associated with leaks. Summary of the Invention

[0003] This application provides a method, apparatus, and electronic device for measuring compressed air leakage and injection distance. It solves the problems in related technologies where strong noise and heat background interference make it impossible to achieve non-contact, synchronous, visual identification of compressed air leakage, accurate quantitative calculation of leakage and injection distance, and comprehensive, intuitive assessment of leakage risk.

[0004] According to a first aspect of this application, a method for measuring compressed air leakage and injection distance is provided, comprising:

[0005] The original schlieren images of the flow field around the pipeline area under test are continuously acquired using a schlieren imaging system, and the ambient background temperature, ambient background pressure, and temperature and pressure parameters of the pipeline's internal operating conditions are acquired simultaneously. The original schlieren image is processed by AI feature extraction algorithm to identify the morphological characteristics of the leaking airflow and classify the leakage mode, while calculating the two-dimensional deflection angle distribution of the flow field. The three-dimensional density field of the flow field is reconstructed based on the two-dimensional deflection angle distribution, and combined with the two-dimensional velocity field resolved from the original schlieren image to calculate the mass flow rate of the leaked gas. Based on the theory of high-speed compressible jets, and combined with mass flow rate, pipeline operating parameters and environmental parameters, the effective jet distance of the leaking gas is calculated. The calculated leak location, leak volume, and jet impact range are mapped onto the three-dimensional digital model of the pipeline for visualization rendering and display.

[0006] According to a second aspect of this application, an apparatus for measuring compressed air leakage and injection distance is provided, comprising: The acquisition module is configured to continuously acquire raw schlieren images of the flow field around the pipeline area under test using a schlieren imaging system, and simultaneously acquire ambient background temperature, ambient background pressure, and temperature and pressure parameters of the pipeline's internal operating conditions. The identification module is configured to process the original schlieren image using an AI feature extraction algorithm, identify the morphological characteristics of the leaking airflow and classify the leakage mode, and calculate the two-dimensional deflection angle distribution of the flow field. The first calculation module is configured to reconstruct the three-dimensional density field of the flow field based on the two-dimensional deflection angle distribution, and combine it with the two-dimensional velocity field resolved from the original schlieren image to calculate the mass flow rate of the leaked gas. The second calculation module is configured to calculate the effective jet distance of the leaking gas based on the high-speed compressible jet theory, combined with mass flow rate, pipeline operating parameters and environmental parameters. The mapping module is configured to map the calculated leak location, leak volume, and jet impact range onto the three-dimensional digital model of the pipeline for visualization rendering and display.

[0007] According to a third aspect of this application, an electronic device is provided, comprising: At least one processor; and memory that is communicatively connected to at least one processor; The memory stores instructions that can be executed by at least one processor to enable the at least one processor to perform the aforementioned method for measuring compressed air leakage and injection distance in the first aspect.

[0008] According to a fourth aspect of this application, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to perform the aforementioned method of measuring compressed air leakage and injection distance according to the first aspect.

[0009] According to a fifth aspect of this application, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method for measuring compressed air leakage and injection distance as described in the first aspect above.

[0010] This application utilizes a schlieren imaging system to continuously acquire raw schlieren images of the flow field in the pipeline under test, simultaneously collecting temperature and pressure parameters of the environment and the pipeline's internal operating conditions. AI feature extraction algorithms process the schlieren images to identify the morphological characteristics of the leaking gas flow, classify the leak mode, and calculate the two-dimensional deflection angle distribution of the flow field. Based on the two-dimensional deflection angle distribution, a three-dimensional density field of the flow field is reconstructed, and the leaking gas mass flow rate is calculated by combining it with the analyzed two-dimensional velocity field. Then, based on the high-speed compressible jet theory and relevant parameters, the effective jet distance of the leaking gas flow is calculated. Finally, the leak-related data is mapped onto a three-dimensional digital model of the pipeline for visualization and rendering. Therefore, this application solves the problems in related technologies where strong noise and intense heat background interference prevent non-contact, simultaneous, and accurate quantitative calculation of leak volume and jet distance, making it difficult to comprehensively and intuitively assess leak risks. It achieves non-contact, highly interference-resistant, and visualized detection of compressed air leaks, simultaneously and accurately quantifying the leak mass flow rate and effective jet distance, and intuitively presenting the leak location and impact range. This significantly improves the accuracy, robustness, and on-site maintenance safety of high-temperature and high-pressure pipeline leak detection.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 A schematic flowchart illustrating a method for measuring compressed air leakage and injection distance provided in an embodiment of this application; Figure 2 This is a schematic diagram of a device for measuring compressed air leakage and injection distance, provided in an embodiment of this application. Detailed Implementation

[0014] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0015] In this embodiment, the system is configured to address the high-temperature pipeline leakage problem in the compressed air energy storage power station, where the temperature of the high-pressure air inside the pipeline is 450°C and the pressure is 10MPa.

[0016] The following describes, with reference to the accompanying drawings, a method, apparatus, and electronic device for measuring compressed air leakage and injection distance according to embodiments of this application.

[0017] Figure 1 This is a schematic flowchart illustrating a method for measuring compressed air leakage and injection distance provided in an embodiment of this application.

[0018] like Figure 1 As shown, the method includes the following steps: Step 101: Use a schlieren imaging system to continuously acquire raw schlieren images of the flow field around the pipeline area to be tested, and simultaneously acquire ambient background temperature, ambient background pressure, and temperature and pressure parameters of the pipeline's internal operating conditions.

[0019] In some embodiments, the schlieren imaging system employs a background-oriented schlieren structure. Core components include a high-frequency point light source, a collimating lens, a focusing lens, an adjustable blade edge, and a high-speed industrial camera. In actual deployment, a high-power nanosecond pulsed laser with a center wavelength of 532nm is used as the detection light source, paired with a parabolic mirror with a diameter of 300mm and a focal length of 2500mm to construct the optical path. The blade edge cutting ratio is set to 50%. The high-speed industrial camera is a CMOS camera with a global shutter, a resolution of 1280×1024, a frame rate of 2000fps, and a shutter time compressed to 10μs. This allows for precise capture of the high-frequency turbulent vortex structure generated by the high-temperature, high-pressure air jet, ensuring the temporal and spatial accuracy of the original schlieren image.

[0020] During synchronous data acquisition, high-precision platinum resistance thermometers and pressure transmitters are used to obtain the ambient background temperature and pressure of the measurement area, as well as the temperature and pressure of the pipeline's internal operating conditions. The acquisition action is synchronized with the high-speed camera via a TTL level hardware trigger, and each frame of schlieren image is matched with the corresponding timestamp of operating conditions and environmental parameters to ensure the spatiotemporal consistency of the data.

[0021] The high-sensitivity schlieren imaging system transforms the invisible gas flow field into a visual image. The synchronously matched temperature and pressure parameters provide precise boundary conditions, enabling non-contact flow field data acquisition. This avoids the safety risks of contact measurement under high temperature and high pressure conditions, while also possessing strong resistance to environmental interference.

[0022] Step 102: Process the original schlieren image using an AI feature extraction algorithm to identify the morphological characteristics of the leaking airflow and classify the leakage mode, while calculating the two-dimensional deflection angle distribution of the flow field.

[0023] In some embodiments, to address background noise and thermal convection interference in the original schlieren images from industrial sites, the algorithm first performs dynamic background removal using an improved ViBe algorithm to distinguish between low-speed buoyancy thermal convection and high-speed momentum-dominated leakage jets. Then, a lightweight recognition network based on MaskR-CNN is used to extract the morphological features of the leaking airflow. This network is pre-trained on 50,000 sets of high-pressure jet schlieren data covering point, line, area, and diffusion patterns. It can classify leakage patterns based on the aspect ratio of the airflow morphology; an aspect ratio less than 1.2 is classified as axisymmetric jets, and an aspect ratio greater than 3 is classified as crack leakage. Simultaneously, the two-dimensional deflection angle distribution calculation is performed. By normalizing the brightness and contrast of the preprocessed schlieren image, pixel-level calculations are completed based on the light intensity ratio method. The core calculation formula is:

[0024] in, 'a' is the focal length of the mirror, and 'a' is the width of the unobstructed portion of the blade edge. The angle of light deflection is used to generate a two-dimensional heat map of the deflection angle distribution across the entire field of view.

[0025] By using AI algorithms to accurately filter out environmental interference, the system can automatically identify and classify leaked airflow, and simultaneously calculate the two-dimensional deflection angle distribution of the flow field, providing reliable basic data for subsequent quantitative analysis of the flow field and significantly improving the robustness and automation of the detection system.

[0026] Step 103: Reconstruct the three-dimensional density field of the flow field based on the two-dimensional deflection angle distribution, and calculate the mass flow rate of the leaked gas by combining it with the two-dimensional velocity field resolved from the original schlieren image.

[0027] In some embodiments, for axisymmetric leakage flow fields, the radial refractive index gradient distribution on the cross section is inverted from the two-dimensional deflection angle distribution using the inverse Abelian transform, and the integral equation is discretized and solved using the Nesting-Knots algorithm. The core formula is:

[0028] In the formula, r is the radial coordinate of the jet section, and R is the radius of the jet boundary.

[0029] The conversion from refractive index to gas density is accomplished using the Gladstone-Dale relation, which is: where n is the refractive index. Let K be the gas density and K be the Gladstone-Dale constant, and then the three-dimensional density field of the flow field can be reconstructed.

[0030] The two-dimensional velocity field was obtained analytically by tracing the pixel displacement of turbulent vortices in the schlieren image using the dense optical flow method. An integral section was selected in the fully developed jet region at a distance of 5 times the equivalent diameter from the leak opening, and the leakage mass flow rate was solved by spatial integration. The calculation formula is as follows:

[0031] In the formula, v(x,y) represents the velocity distribution of the two-dimensional flow field; The reconstructed density field is given, where A is the cross-section of the leakage jet. This refers to the leakage mass flow rate.

[0032] This step achieves accurate inversion from optical features to flow field thermodynamic parameters, avoiding calculation errors caused by shock wave structures near the leak. The accuracy of mass flow rate measurement can reach ±5%, providing accurate quantitative data support for leakage energy loss assessment.

[0033] Step 104: Based on the high-speed compressible jet theory, and combined with mass flow rate, pipeline operating parameters and environmental parameters, calculate the effective jet distance of the leaking gas flow.

[0034] In some embodiments, the calculation process is based on a high-speed compressible turbulent free jet attenuation model, and the calculation system is constructed based on the laws of conservation of momentum and energy. When high-pressure gas is ejected outward from the leak, it continuously entrains the surrounding still ambient air, and the velocity and temperature along the jet centerline decrease regularly with axial distance. In this step, the effective jet distance is defined as the maximum axial physical distance traveled by the airflow when the jet centerline velocity decreases to a safe threshold of 1 m / s and the centerline temperature decreases to a safe threshold of 50°C.

[0035] The calculation process uses the initial operating temperature and pressure inside the pipeline as the boundary conditions of the jet outlet. It combines the ambient background temperature and pressure parameters to correct the turbulent entrainment rate, and iteratively calculates the axial attenuation law of the jet parameters by coupling the solved leakage mass flow rate. Simultaneously, it combines the jet's inherent divergence angle of 11.8°~12.5° to match the airflow influence range corresponding to the injection distance.

[0036] The beneficial effect of this step is that it accurately quantifies the effective impact distance of the leaked gas flow, clarifies the safety risk boundary caused by the leak, and provides an accurate quantitative basis for on-site safety operation and maintenance and risk classification and control. It can effectively predict the safety threat of the leaked gas flow to surrounding equipment and personnel.

[0037] Step 105: Map the calculated leak location, leak volume, and jet impact range onto the three-dimensional digital model of the pipeline for visualization rendering and display.

[0038] In some embodiments, the solvePnP algorithm is first used to complete the real-time spatial alignment between the schlieren image coordinate system and the three-dimensional BIM model of the pipeline by using inherent feature points such as flange bolts and elbow edges on the pipeline, and to establish a one-to-one mapping relationship between image pixel coordinates and three-dimensional model spatial coordinates to ensure the spatial accuracy of data mapping.

[0039] The calculated spatial coordinates of the leak point, instantaneous leakage, cumulative leakage, and jet influence range generated based on the effective injection distance are then precisely mapped to the corresponding pipe segment location in the three-dimensional digital model using a reverse spatial intersection algorithm.

[0040] During the visualization rendering process, the system highlights the leak point and uses a dynamic three-dimensional plume model to render the jet's impact range. Simultaneously, quantitative data related to the leakage amount are overlaid at the corresponding positions on the model, achieving an integrated visualization display of the leak location, leakage severity, and impact range.

[0041] By transforming abstract quantitative leakage data into intuitive 3D visualizations, the system achieves precise matching between leakage information and pipeline entity models. This helps maintenance personnel quickly locate leak points, intuitively grasp the scope of leakage risks, and significantly improve the efficiency and accuracy of on-site leak handling and control.

[0042] Compared with related technologies, in this embodiment, the original schlieren images of the flow field around the pipeline area under test are continuously acquired using a schlieren imaging system, while simultaneously acquiring ambient background temperature, ambient background pressure, and temperature and pressure parameters of the pipeline's internal operating conditions. The original schlieren images are processed using an AI feature extraction algorithm to identify the morphological characteristics of the leaking gas flow and classify the leakage mode, while simultaneously calculating the two-dimensional deflection angle distribution of the flow field. Based on the two-dimensional deflection angle distribution, the three-dimensional density field of the flow field is reconstructed, and combined with the two-dimensional velocity field parsed from the original schlieren images, the mass flow rate of the leaking gas is calculated. Based on the high-speed compressible jet theory, combined with the mass flow rate, pipeline operating parameters, and environmental parameters, the effective jet distance of the leaking gas flow is calculated. The calculated leak location, leak volume, and jet influence range are mapped onto a three-dimensional digital model of the pipeline for visualization rendering and display. This technology can solve the problems in related technologies where strong noise and heat background interference make it impossible to achieve non-contact synchronous visual identification of compressed air leaks, accurate quantitative calculation of leak volume and injection distance, and comprehensive and intuitive assessment of leak risks. It achieves non-contact, highly interference-resistant visual detection of compressed air leaks, synchronously and accurately quantifies the leak mass flow rate and effective injection distance, and intuitively presents the leak location and impact range, significantly improving the accuracy, robustness, and on-site operation and maintenance safety of high-temperature and high-pressure pipeline leak detection.

[0043] As a specific embodiment of this application, based on the basic scheme, the schlieren imaging system is further defined as a background directional schlieren system, including a high-frequency point light source, a collimating lens, a focusing lens, an adjustable blade edge, and a high-speed industrial camera with a global shutter, wherein the frame rate of the high-speed industrial camera is not less than 1000fps.

[0044] Specifically, the high-frequency point light source uses a high-power nanosecond pulsed laser with a center wavelength of 532nm, which can effectively filter optical path interference caused by strong background heat radiation in industrial environments and output a stable detection beam. After being collimated by a collimating lens, the beam forms a uniform parallel beam that completely covers the monitoring area of ​​the pipe under test. When the parallel beam passes through the leaking airflow field with a density gradient, wavefront phase distortion and local light deflection will occur due to the change in refractive index within the flow field. The deflected light carrying flow field information is converged by a focusing lens and projected onto an adjustable blade at the focal plane of the optical path. The adjustable blade can selectively block the deflected light, converting the flow field density gradient changes invisible to the human eye into an alternating light intensity distribution of bright and dark areas that can be captured by the target surface of a high-speed industrial camera, thus completing the optical conversion of flow field information.

[0045] The high-speed industrial camera is equipped with a global shutter with a frame rate of no less than 1000fps. In practical engineering applications, the frame rate can be set to 2000fps, and the shutter time can be compressed to 10μs simultaneously. The camera resolution is set to 1280×1024, and the sampling depth is 12bit. It can accurately capture the high-frequency turbulent vortex and transient shock wave structure generated by high-temperature and high-pressure air jets, completely avoiding motion blur caused by rolling shutter and ensuring the temporal and spatial resolution of the original schlieren image.

[0046] This embodiment, through an optimized background-oriented schlieren optical path design, combined with a high-frame-rate global shutter industrial camera, significantly improves the acquisition accuracy and anti-interference capability of flow field schlieren images in complex industrial environments, providing a high-quality raw image data foundation for subsequent quantitative analysis of leaked airflow.

[0047] As a specific embodiment of this application, based on the basic solution, it further specifies that the original schlieren image is processed using an AI feature extraction algorithm to identify the morphological characteristics of the leaking airflow and classify the leakage mode, including: The AI ​​feature extraction algorithm uses a pre-trained convolutional neural network to extract flow field morphological features from a continuous schlieren image sequence, outputs the geometric morphology probability matrix of the leakage source, and automatically calls the corresponding three-dimensional density field reconstruction algorithm based on the identified leakage morphology. Leakage patterns include at least flange seam surface leakage, weld micropore point leakage, and pipeline crack line leakage.

[0048] Specifically, the AI ​​feature extraction algorithm is based on a pre-trained convolutional neural network. This network adopts a lightweight network architecture based on an improvement of Mask R-CNN. It was pre-trained and optimized using 50,000 sets of high-pressure jet schlieren datasets collected in a laboratory environment, covering point, line, area, and diffusion patterns, demonstrating strong adaptability to industrial environments and high feature recognition accuracy. The algorithm takes continuously acquired schlieren image sequences as input and performs multi-scale morphological feature extraction on the flow field regions in the images, accurately capturing core morphological features such as the topology, aspect ratio, and turbulence distribution of the leaking airflow. After feature extraction, the network outputs a geometric morphology probability matrix corresponding to the leak source. This matrix contains the matching probability of different leak morphologies with the extracted features. The system selects the type with the highest matching probability as the final identified leak morphology.

[0049] The algorithm can identify at least the following leakage morphologies: flange seam planar leakage, weld seam micropore point leakage, and pipeline crack linear leakage. Based on the identified leakage morphology, the system automatically matches and invokes the corresponding 3D density field reconstruction algorithm. For axisymmetric morphologies such as weld seam micropore point leakage, the system automatically invokes the inverse Abelian transform reconstruction algorithm; for non-axisymmetric morphologies such as flange seam planar leakage and pipeline crack linear leakage, the system automatically invokes the multi-angle CT projection reconstruction algorithm.

[0050] By using a pre-trained convolutional neural network, the automatic and high-precision identification and classification of leakage patterns can be achieved. This can be adapted to various common pipeline leakage scenarios in industrial sites. At the same time, by automatically matching the leakage pattern with the reconstruction algorithm, the accuracy and computational efficiency of subsequent three-dimensional density field reconstruction of the flow field are greatly improved, reducing the cost of manual intervention and ensuring the stability and accuracy of leakage detection under complex working conditions.

[0051] As a specific embodiment of this application, based on the basic scheme, the two-dimensional velocity field is further defined as being obtained by calculating the pixel displacement of fluid micro-clusters in two adjacent frames of schlieren images using the optical flow method.

[0052] Specifically, the leaked high-temperature, high-pressure airflow exhibits strong turbulent characteristics. The jet is filled with turbulent vortices and vortex shedding structures of varying sizes. These structures display stably traceable light and dark texture features in schlieren images, serving as natural tracer particles for flow field velocity calculations. No additional tracer medium needs to be added to the flow field, making it perfectly suited for non-contact measurement requirements. This embodiment employs the Farneback dense optical flow method to analyze the velocity field. Based on a sequence of schlieren images continuously acquired by a high-speed industrial camera, two adjacent frames with a time interval of less than 1 ms are selected. By extracting the spatial displacement vectors of the corresponding pixels of the fluid micro-elements in the images, the transient two-dimensional velocity distribution of the flow field is calculated. The core calculation formula is:

[0053] In the formula , These represent the spatial displacements of the fluid micro-element pixels in the x and y directions, respectively. The time interval between the acquisition of two adjacent schlieren images. , These are the velocity components of the fluid micro-particles at the corresponding locations in the x and y directions, respectively. During the calculation, the axial component of the velocity is extracted as the main component to match the requirements of the subsequent integral calculation of mass flow rate.

[0054] To ensure the accuracy of velocity calculation, this embodiment performs matching optimization by extracting SIFT feature points between two image frames. Simultaneously, it performs velocity verification by tracking the tilt angle β of the Mach wave in the schlieren image. The verification formula is as follows: Where M is the local Mach number, calculated using the local sound speed formula. Independent verification of flow velocity was completed, further improving the accuracy of velocity field analysis.

[0055] By relying on the turbulent structure of the leaking airflow itself as a tracer feature, the optical flow method achieves non-contact, high-precision analysis of the two-dimensional velocity of the entire flow field. No additional modifications to the flow field and measurement environment are required, making it suitable for industrial field conditions with high temperature, high pressure, and strong interference. This provides a reliable velocity field data foundation for the accurate calculation of leaked mass flow rate.

[0056] As a specific implementation of this application, based on the basic scheme, the effective spray distance is further defined as the maximum axial distance experienced when the jet centerline velocity decays to a preset safe velocity threshold or the jet centerline temperature decays to a preset safe temperature threshold under ambient background temperature and pressure.

[0057] Specifically, this definition is based on the attenuation characteristics of high-speed compressible turbulent free jets. After high-temperature, high-pressure gas is ejected from a pipeline leak, it continuously entrains still air in the surrounding environment, resulting in intense turbulent mixing. The momentum and heat along the jet centerline exhibit a regular attenuation along the jet axis, and its safety threat to surrounding personnel and equipment gradually decreases with increasing axial distance. This implementation uses a dual-threshold judgment rule to simultaneously cover the dynamic impact risk and thermal burn risk of the leaking gas. The preset safe velocity threshold can be set to 1 m / s according to the on-site conditions. This threshold is a critical safety value that will not cause dust to fly on-site or cause erosion damage to surrounding instrument cables. The preset safe temperature threshold can be set to 50℃, which is a critical safety value that will not cause burns to personnel upon contact.

[0058] In the actual calculation process, the system uses the synchronously collected temperature and pressure inside the pipeline as the initial boundary conditions of the jet outlet. It combines the real-time environmental background temperature and pressure parameters to correct the turbulent entrainment rate, and iteratively solves the axial decay curve of the jet centerline velocity and temperature through the momentum conservation and energy conservation equations. The axial distance corresponding to the first time any safety threshold is reached is taken as the final effective injection distance.

[0059] By defining thresholds in a dual-dimensional manner, the system comprehensively covers the two core safety risks brought about by leaked gas flow, clarifies the quantitative boundaries of the leakage impact range, adapts to the safety management and control needs of different scenarios in industrial sites, and provides accurate and practical quantitative basis for on-site risk classification and control and leakage emergency response, avoiding the omission of safety risks caused by single indicator judgment.

[0060] As a specific implementation of this application, based on the basic scheme, the three-dimensional digital model of the pipeline is further defined as a 3D information model of the pipeline. The system uses a reverse spatial intersection algorithm to overlay and display the spatial coordinates of the leak point, the leakage data, and the jet hazard envelope generated based on the effective injection distance on the 3D information model in real time.

[0061] Specifically, the 3D information model of the pipeline is a BIM three-dimensional information model that perfectly matches the physical dimensions and spatial location of the pipeline network to be tested on site. The model contains all the physical features of the pipeline, such as pipe diameter, direction, flanges, welds, elbows, supports and hangers, and their corresponding spatial coordinate information, providing an accurate reference carrier for the spatial mapping and visualization of leakage data.

[0062] The system first uses inherent feature points on the pipeline, such as flange bolts and elbow edges, to accurately register the schlieren image pixel coordinate system, the on-site world coordinate system, and the 3D information model spatial coordinate system, establishing a one-to-one spatial mapping relationship between the multiple coordinate systems. Based on this, through a reverse spatial intersection algorithm, the system accurately matches and mounts the real-time calculated spatial coordinates of the leak point, instantaneous leakage volume, cumulative leakage volume data, and the jet hazard envelope generated based on the effective injection distance and the inherent jet divergence angle of 11.8°~12.5° onto the corresponding pipe segment location in the 3D information model.

[0063] During the visualization process, the system highlights the leak points on the 3D information model, renders the jet hazard envelope using a dynamic three-dimensional plume model, and simultaneously overlays quantitative data of the leakage amount at the corresponding locations, achieving an integrated real-time presentation of the leak location, leakage severity, and hazard impact range.

[0064] The reverse spatial intersection algorithm achieves accurate spatial matching between dynamic leakage data and 3D information models of pipeline entities, transforming abstract quantitative leakage data into intuitive 3D visualization content. This helps maintenance personnel quickly locate leakage points and intuitively grasp the leakage hazard boundaries, significantly improving the accuracy of pipeline leakage control and emergency response efficiency in industrial sites.

[0065] As a specific implementation of this application, based on the basic scheme, the pipeline to be tested is further defined as a high-temperature heat exchanger pipeline in a compressed air energy storage system, a high-pressure gas storage chamber connection pipeline, or a high-pressure air supply and secondary air pipeline in a boiler system of a thermal power plant. The schlieren imaging system is equipped with an infrared-visible dual-spectral filter to suppress the interference of high-temperature background thermal radiation on the imaging.

[0066] Specifically, the pipelines under test are high-temperature heat exchanger pipelines and high-pressure air storage chamber connection pipelines in compressed air energy storage systems, or high-pressure air supply and secondary air pipelines in boiler systems of thermal power plants. These pipelines operate under harsh conditions of high temperature and high pressure, with compressed air temperatures exceeding 300°C and pressures ranging from 5MPa to 15MPa. Due to factors such as alternating thermal stress, mechanical vibration, weld fatigue, and aging of flange seals, they are highly susceptible to subtle, hidden leaks. The high-speed jets generated by these leaks pose both a high-kinetic-energy impact risk and a risk of thermal burns, making this a key and challenging scenario for industrial pipeline leak detection. Conventional detection methods are insufficient for accurate and safe operation.

[0067] To address the prevalent problem of strong background high-temperature thermal radiation interference in the aforementioned scenarios, this embodiment equips the schlieren imaging system with an infrared-visible dual-spectrum filter. This filter allows precise transmission of the 532nm visible light probe light beam used by the system, while effectively blocking infrared stray light generated by high-temperature pipes and equipment on-site. This suppresses the image signal-to-noise ratio degradation and flow field detail obscuration caused by strong thermal background stray light entering the imaging optical path, thus stably ensuring the imaging quality and flow field detail clarity of the original schlieren image.

[0068] This implementation clearly defines the core applicable industrial scenarios for the solution, specifically addressing the industry pain point of strong thermal background radiation interference imaging in high-temperature and high-pressure pipelines. It significantly improves the system's environmental adaptability and detection stability in complex industrial sites such as compressed air energy storage stations and thermal power plants, ensuring the accuracy and operational safety of leak detection under harsh operating conditions.

[0069] Figure 2 This is a schematic diagram of a device for measuring compressed air leakage and injection distance provided in an embodiment of this application, as shown below. Figure 2 As shown, it includes: acquisition module 201, recognition module 202, first calculation module 203, and second calculation module 204.

[0070] The acquisition module 201 is configured to continuously acquire raw schlieren images of the flow field around the pipeline area under test using a schlieren imaging system, and simultaneously acquire ambient background temperature, ambient background pressure, and temperature and pressure parameters of the pipeline's internal operating conditions. The identification module 202 is configured to process the original schlieren image through an AI feature extraction algorithm, identify the morphological characteristics of the leaking airflow and classify the leakage mode, and at the same time calculate the two-dimensional deflection angle distribution of the flow field. The first calculation module 203 is configured to reconstruct the three-dimensional density field of the flow field based on the two-dimensional deflection angle distribution, and combine it with the two-dimensional velocity field resolved from the original schlieren image to calculate the mass flow rate of the leaked gas. The second calculation module 204 is configured to calculate the effective jet distance of the leaking gas based on the high-speed compressible jet theory, combined with mass flow rate, pipeline operating condition parameters and environmental parameters. The mapping module 205 is configured to map the calculated leak location, leak amount and jet impact range to the three-dimensional digital model of the pipeline for visualization rendering and display.

[0071] It should be noted that other corresponding descriptions of the functional units involved in the device for measuring compressed air leakage and injection distance provided in this embodiment can be found in [reference needed]. Figure 1 The corresponding description in [the document] will not be repeated here.

[0072] Based on the above, Figure 1 The present embodiment describes a method for measuring compressed air leakage and injection distance. Correspondingly, this embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method. Figure 1 This illustrates a method for measuring compressed air leakage and injection distance.

[0073] Based on the above, Figure 1 The present embodiment describes a method for measuring compressed air leakage and injection distance. Correspondingly, this embodiment also provides a computer program product on which a computer program is stored. When executed by a processor, this computer program implements the above-described... Figure 1 This illustrates a method for measuring compressed air leakage and injection distance.

[0074] Based on this understanding, the technical solution of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as CD-ROM, USB flash drive, mobile hard drive, etc.) and includes several instructions to cause a computer device (such as personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of this application.

[0075] Based on the above, Figure 1 The method shown is for measuring compressed air leakage and injection distance, and Figure 2 To achieve the above objectives, the present application also provides an electronic device, such as a personal computer or a server, in the illustrated virtual device embodiment. This device includes a storage medium and a processor; the storage medium stores a computer program; the processor executes the computer program to implement the above-described virtual device. Figure 1 This illustrates a method for measuring compressed air leakage and injection distance.

[0076] In some embodiments, the aforementioned physical device may further include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, an input unit such as a keyboard, etc., and optionally, a USB interface, a card reader interface, etc. In some embodiments, the network interface may include a standard wired interface, a wireless interface (such as a Wi-Fi interface), etc.

[0077] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the aforementioned physical device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software in the information processing physical device.

[0078] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0079] The above are merely specific embodiments of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to these embodiments, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method of measuring the amount of compressed air leakage and the distance of a jet, characterized in that, include: The original schlieren images of the flow field around the pipeline area under test are continuously acquired using a schlieren imaging system, and the ambient background temperature, ambient background pressure, and temperature and pressure parameters of the pipeline's internal operating conditions are acquired simultaneously. The original schlieren image is processed by an AI feature extraction algorithm to identify the morphological characteristics of the leaking airflow and classify the leakage mode, while calculating the two-dimensional deflection angle distribution of the flow field. The three-dimensional density field of the flow field is reconstructed based on the two-dimensional deflection angle distribution, and the mass flow rate of the leaked gas is calculated by combining it with the two-dimensional velocity field resolved from the original schlieren image. Based on the high-speed compressible jet theory, and combined with the mass flow rate, pipeline operating parameters and environmental parameters, the effective jet distance of the leaking gas is calculated. The calculated leak location, leak volume, and jet impact range are mapped onto the three-dimensional digital model of the pipeline for visualization rendering and display.

2. The method of claim 1, wherein, The schlieren imaging system is a background-oriented schlieren system, including a high-frequency point light source, a collimating lens, a focusing lens, an adjustable blade edge, and a high-speed industrial camera with a global shutter, wherein the frame rate of the high-speed industrial camera is not less than 1000fps.

3. The method of claim 1, wherein, The process of processing the original schlieren image using an AI feature extraction algorithm to identify the morphological characteristics of the leaking airflow and classify the leak pattern includes: The AI ​​feature extraction algorithm uses a pre-trained convolutional neural network to extract flow field morphological features from a continuous schlieren image sequence, outputs the geometric morphology probability matrix of the leakage source, and automatically calls the corresponding three-dimensional density field reconstruction algorithm based on the identified leakage morphology. The leakage patterns include at least flange seam surface leakage, weld micropore point leakage, and pipeline crack line leakage.

4. The method of claim 1, wherein, The two-dimensional velocity field is obtained by calculating the pixel displacement of fluid micro-clusters in two adjacent schlieren images using the optical flow method.

5. The method of claim 1, wherein, The effective jetting distance is defined as the maximum axial distance traveled when the jet centerline velocity decays to a preset safe velocity threshold or the jet centerline temperature decays to a preset safe temperature threshold under the ambient background temperature and pressure.

6. The method of claim 1, wherein, The pipeline's three-dimensional digital model is a 3D information model of the pipeline. The system uses a reverse spatial intersection algorithm to overlay and display the spatial coordinates of the leak point, the leakage amount data, and the jet hazard envelope generated based on the effective injection distance onto the 3D information model in real time.

7. The method for measuring compressed air leakage and injection distance according to claim 1, characterized in that, The pipeline to be tested is a high-temperature heat exchanger pipeline in a compressed air energy storage system, a high-pressure gas storage chamber connection pipeline, or a high-pressure air supply and secondary air pipeline in a boiler system of a thermal power plant. The schlieren imaging system is equipped with an infrared-visible dual-spectral filter to suppress the interference of high-temperature background thermal radiation on imaging.

8. A device for measuring compressed air leakage and injection distance, characterized in that, include: The acquisition module is configured to continuously acquire raw schlieren images of the flow field around the pipeline area under test using a schlieren imaging system, and simultaneously acquire ambient background temperature, ambient background pressure, and temperature and pressure parameters of the pipeline's internal operating conditions. The identification module is configured to process the original schlieren image using an AI feature extraction algorithm, identify the morphological characteristics of the leaking airflow and classify the leakage mode, and simultaneously calculate the two-dimensional deflection angle distribution of the flow field. The first calculation module is configured to reconstruct the three-dimensional density field of the flow field based on the two-dimensional deflection angle distribution, and combine it with the two-dimensional velocity field resolved from the original schlieren image to calculate the mass flow rate of the leaked gas. The second calculation module is configured to calculate the effective jet distance of the leaking gas flow based on the high-speed compressible jet theory, combined with the mass flow rate, pipeline operating parameters and environmental parameters. The mapping module is configured to map the calculated leak location, leak volume, and jet impact range onto the three-dimensional digital model of the pipeline for visualization rendering and display.

9. An electronic device, characterized in that, include: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method for measuring compressed air leakage and injection distance as described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method for measuring compressed air leakage and injection distance according to any one of claims 1-7.

Images