A compressed air energy storage system chamber plug gas leak monitoring method and apparatus

Abstract

The present application relates to the technical field of energy storage safety monitoring, and discloses a compressed air energy storage system chamber plug gas leakage monitoring method and device, in the method, non-contact schlieren image acquisition is used, combined with image preprocessing method to offset the influence of complex environment such as chamber light fluctuation, dust interference, and then the two-stage gray scale contrast method is used to accurately capture the pixel-level gray scale change of the leakage abnormal area in the image; the corrected gas density conversion mapping model converts the dynamic process of the compressed air energy storage system chamber plug gas leakage into a more convenient monitoring gas density change, and finally, according to the set early warning threshold, the plug area gas leakage monitoring result in the target chamber is accurately determined, and the defect that the gas leakage monitoring method in the related art cannot accurately monitor the gas leakage of the chamber plug area of the compressed air energy storage system is effectively overcome.

Description

Technical Field

[0001] This invention relates to the field of energy storage safety monitoring technology, specifically to a method and device for monitoring gas leakage at the chamber plug of a compressed air energy storage system. Background Technology

[0002] Compressed air energy storage systems typically use underground chambers as the storage medium for high-pressure air. The chamber's airtightness is crucial for ensuring the system's safe and efficient operation. The plug, as a vital sealing structure within the chamber, directly impacts the system's operational stability and safety. During long-term operation, factors such as the continuous action of high-pressure air, deformation of the surrounding rock, and aging of the plug material can easily lead to gas leakage at the plug. Once leakage occurs, it not only reduces energy storage efficiency and wastes energy but can also trigger sudden pressure changes and surrounding rock instability, seriously threatening the system's operational safety. Therefore, real-time and accurate monitoring of gas leakage at the plugs in compressed air energy storage system chambers is of paramount importance.

[0003] The gas leak monitoring methods disclosed in the related technologies include: pressure sensor monitoring method and gas sensor monitoring method. The pressure sensor monitoring method determines whether there is a leak by monitoring the pressure difference between the inside and outside of the chamber; while the gas sensor monitoring method requires placing sensors in the area where a leak may occur for detection.

[0004] However, the high pressure and high humidity environment inside compressed air energy storage systems can easily affect the lifespan and monitoring accuracy of sensors, and they are also less sensitive to minor leaks. Therefore, the gas leak monitoring methods disclosed in related technologies are difficult to accurately monitor gas leaks in the chamber plug area of ​​compressed air energy storage systems. Summary of the Invention

[0005] This invention provides a method and apparatus for monitoring gas leakage at the chamber plug of a compressed air energy storage system, thereby solving the problem that gas leakage monitoring methods disclosed in related technologies are difficult to accurately monitor gas leakage in the chamber plug area of ​​a compressed air energy storage system.

[0006] In a first aspect, the present invention provides a method for monitoring gas leakage at the plug of a compressed air energy storage system chamber, the method comprising: Real-time schlieren images of the target chamber plug area of ​​the compressed air energy storage system were acquired; Based on the real-time schlieren image, a preprocessed schlieren image is obtained using a preset image preprocessing method; Based on the preprocessed schlieren image, combined with the reference schlieren image of the corresponding chamber plug area, the grayscale difference value of the grayscale change abnormal area is obtained by using a two-stage grayscale comparison method; the reference schlieren image includes the schlieren image in a leak-free state after eliminating environmental noise. Based on the gray-level difference in the gray-level change anomaly region, the gas density change is obtained using the modified gas density conversion mapping model. Based on the gas density change and the early warning threshold of the target chamber, the gas leakage monitoring results of the plugged area of ​​the target chamber are obtained.

[0007] Through the above implementation method, non-contact schlieren image acquisition is used, combined with image preprocessing methods to offset the influence of complex environments such as chamber light fluctuations and dust interference. Then, a two-stage grayscale comparison method is used to accurately capture pixel-level grayscale changes in the leakage abnormal area in the image. The corrected gas density conversion mapping model realizes the transformation of the dynamic process of gas leakage in the chamber plug of the compressed air energy storage system into a more convenient gas density change. Finally, based on the set warning threshold, the gas leakage monitoring result of the plug area in the target chamber is accurately determined. This effectively overcomes the shortcomings of gas leakage monitoring methods in related technologies that are difficult to accurately monitor the gas leakage in the plug area of ​​the compressed air energy storage system chamber, and greatly improves the identification accuracy and monitoring stability of gas leakage in the plug area of ​​the compressed air energy storage chamber.

[0008] In one optional implementation, obtaining a preprocessed schlieren image based on the real-time schlieren image using a preset image preprocessing method includes: Based on the real-time schlieren image, a grayscale image is obtained by performing grayscale conversion using a dynamic threshold grayscale algorithm. Based on the grayscale image, a denoised schlieren image is obtained by using a filtering algorithm and a morphological opening operation method. Based on the densely gray-scale regions in the denoised schlieren image, a contrast enhancement method is used to process the image to obtain a preprocessed schlieren image.

[0009] Through the above implementation method, in response to the complex operating environment of the compressed air energy storage chamber in the acquired real-time schlieren image, characterized by high pressure, high humidity, light fluctuations, and dust interference, the color image is first converted into a grayscale image using a dynamic threshold grayscale algorithm to eliminate the problem of weak leakage signal loss that is easily caused by fixed threshold grayscale. Then, a combination of filtering algorithm and morphological opening operation is used to accurately remove salt-and-pepper noise and pseudo-interference points formed by tiny dust particles in the image, significantly reducing the impact of chamber environment interference on image quality. Finally, contrast enhancement processing is performed only on the areas with dense grayscale distribution in the denoised image. This not only specifically improves the contrast of weak leakage signal areas and highlights leakage-related image features, but also preserves the grayscale stability of the background area, avoiding the noise amplification problem caused by global contrast enhancement. This effectively overcomes various interferences of the complex chamber environment on the schlieren image, and preserves and enhances the effective image features related to leakage to the greatest extent.

[0010] In one optional implementation, the step of processing the densely gray-level regions in the denoised schlieren image using a contrast enhancement method to obtain a preprocessed schlieren image includes: Based on the densely distributed grayscale regions in the denoised schlieren image, an adaptive histogram equalization method is used to enhance contrast, resulting in a grayscale image that retains the background region, which is then used as the preprocessed schlieren image.

[0011] Through the above implementation method, by performing contrast enhancement processing on the dense gray-scale distribution areas in the denoised schlieren image, the gray-scale contrast of the weak signal area caused by gas leakage in the plug area can be effectively improved and the image features related to leakage can be highlighted. At the same time, the gray-scale stability of the image background area can be preserved to the greatest extent, avoiding the background noise amplification problem caused by global enhancement. From the perspective of image feature optimization, the interference of the complex environment of the chamber on monitoring and analysis is further reduced.

[0012] In one optional implementation, the step of obtaining the grayscale difference value of the abnormal grayscale change area based on the preprocessed schlieren image, combined with the reference schlieren image of the corresponding chamber plug area, using a two-stage grayscale comparison method, includes: Based on the preprocessed schlieren image, combined with the reference schlieren image of the corresponding chamber plug area, the global grayscale variance between the preprocessed schlieren image and the reference schlieren image is obtained; When the global grayscale variance is greater than the coarse judgment threshold, the abnormal grayscale change region in the preprocessed schlieren image is obtained; when the global grayscale variance is less than or equal to the coarse judgment threshold, the global grayscale variance between the preprocessed schlieren image and the reference schlieren image at the next time step is obtained. Based on the abnormal grayscale regions in the preprocessed schlieren image and the corresponding regions in the reference schlieren image, the grayscale difference of the abnormal grayscale regions is obtained using a pixel-by-pixel fine matching comparison method.

[0013] Through the above implementation method, a coarse judgment is first made by obtaining the global grayscale variance between the preprocessed schlieren image and the reference schlieren image. When the global grayscale variance does not exceed the coarse judgment threshold, the analysis directly jumps to the next frame image, which greatly improves the overall monitoring efficiency and effectively avoids invalid pixel-level analysis in the absence of leakage. When the global grayscale variance exceeds the coarse judgment threshold, the abnormal grayscale change area is precisely located. Only the corresponding area of ​​the reference image is compared with the pixel-by-pixel fine matching and the grayscale difference is calculated. This not only focuses on the key areas related to leakage and reduces the amount of computation, but also accurately captures the details of pixel-level grayscale changes and preserves the feature information of weak signals caused by gas leakage to the greatest extent.

[0014] In one optional implementation, the modified gas density conversion mapping model includes: , in, This indicates the change in gas density; Indicates the difference in gray levels of the image; This represents the corrected grayscale-to-angle conversion coefficient; This represents the Gladstone-Dale constant, which is determined based on the type of gas in the chamber plug area and the wavelength of the schlieren light source.

[0015] Through the above implementation method, by utilizing the modified gas density conversion mapping model, the image grayscale difference can be accurately quantified and converted into the gas density change. By incorporating the modified grayscale-deflection angle conversion coefficient, the Gladstone-Dale constant matching the gas type and light wavelength, and the light propagation path length into the quantization calculation, the image feature parameter of grayscale difference can be accurately mapped to the actual physical quantity of gas density. This achieves an effective connection between the leakage signal and the physical quantitative indicator, ensuring the accuracy and scientific nature of the density calculation, and providing objective and accurate quantitative data support for subsequent leakage level determination based on the gas density change threshold.

[0016] In one optional implementation, the warning threshold for the target chamber includes a first threshold, a second threshold, and a third threshold; the step of obtaining the gas leakage monitoring result of the blockage area of ​​the target chamber based on the gas density change and the warning threshold of the target chamber includes: When the change in gas density is greater than or equal to the first threshold and less than the second threshold, the gas leakage monitoring result of the target chamber plug area is a minor leak. When the change in gas density is greater than or equal to the second threshold and less than the third threshold, the gas leakage monitoring result of the target chamber plug area is a moderate leakage. When the change in gas density exceeds the third threshold, the gas leakage monitoring result in the plug area of ​​the target chamber is a serious leak.

[0017] Through the above implementation methods, the first, second, and third thresholds are accurately compared with the gas density change to achieve quantitative judgment of the leakage level. By clearly dividing the numerical range, the gas leakage monitoring results in the corresponding range are judged as minor, moderate, and severe leakage, forming a standardized and quantifiable leakage level judgment rule. This rule can accurately match the actual sealing state of the plug with the degree of leakage development. It not only outputs clear gas leakage monitoring results intuitively, but also provides a clear and unified judgment basis for triggering the subsequent tiered early warning response mechanism, allowing different levels of leakage to be matched with differentiated early warning and handling strategies.

[0018] In one alternative implementation, it further includes: When the change in gas density is greater than or equal to a first threshold, the outline, center coordinates, area, and diffusion rate of the leak area are obtained by using a connected component analysis algorithm and the mapping relationship between the camera's pixel coordinates and the physical size of the plug area.

[0019] Through the above implementation method, after determining that the gas density change has reached the first threshold for leakage, the contour of the abnormal density change area is extracted simultaneously using the connected component analysis algorithm. Combined with the mapping relationship between the camera's pixel coordinates and the physical size of the plug area, the contour, center coordinates, area, and diffusion rate of the leakage area are accurately calculated and quantitatively characterized. This not only completes the determination of the leakage level, but also achieves comprehensive and accurate positioning and dynamic monitoring of the leakage location, range, and diffusion trend, providing accurate and comprehensive spatial and dynamic data support for formulating targeted emergency response and maintenance plans.

[0020] Secondly, the present invention provides a gas leakage monitoring device for a chamber plug in a compressed air energy storage system, the device comprising: The image acquisition module is used to acquire real-time schlieren images of the target chamber plug area of ​​the compressed air energy storage system; The image preprocessing module is used to obtain a preprocessed schlieren image based on the real-time schlieren image using a preset image preprocessing method; An abnormal region identification module is used to obtain the grayscale difference of the abnormal grayscale region based on the preprocessed schlieren image and the reference schlieren image of the corresponding chamber plug region using a two-stage grayscale comparison method; the reference schlieren image includes a schlieren image in a leak-free state after eliminating environmental noise. The data conversion module is used to obtain the gas density change based on the gray level difference in the gray level change abnormal area using the modified gas density conversion mapping model; The result generation module is used to obtain the gas leakage monitoring results of the plugged area of ​​the target chamber based on the gas density change and the early warning threshold of the target chamber.

[0021] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the gas leakage monitoring method for the chamber plug of the compressed air energy storage system described in the first aspect or any corresponding embodiment.

[0022] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the gas leakage monitoring method for the chamber plug of the compressed air energy storage system described in the first aspect or any corresponding embodiment. Attached Figure Description

[0023] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the first process of a method for monitoring gas leakage at the chamber plug of a compressed air energy storage system according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the second process of a method for monitoring gas leakage at the chamber plug of a compressed air energy storage system according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the third process of a method for monitoring gas leakage at the chamber plug of a compressed air energy storage system according to an embodiment of the present invention; Figure 4 This is a structural block diagram of a gas leakage monitoring device for a chamber plug in a compressed air energy storage system according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

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

[0026] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0027] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0028] The gas leak monitoring methods disclosed in related technologies include pressure sensor monitoring and gas sensor monitoring. Pressure sensor monitoring determines the presence of a leak by monitoring changes in the pressure difference between the inside and outside of the chamber; however, this method has low sensitivity to minor leaks and is difficult to pinpoint the leak location. Gas sensor monitoring requires placing sensors in potential leak areas, making it a contact-based monitoring method, which is easily limited by the sensor placement location. Furthermore, the lifespan and monitoring accuracy of the sensors are significantly affected in high-pressure and high-humidity environments.

[0029] To overcome the limitations of existing gas leak monitoring methods in accurately monitoring gas leaks in the plugged areas of compressed air energy storage system chambers, this invention provides a method for monitoring gas leaks in the plugged areas of compressed air energy storage system chambers. This method utilizes non-contact schlieren image acquisition, combined with image preprocessing to offset the influence of complex environmental factors such as chamber light fluctuations and dust interference. A two-stage grayscale comparison method is then used to accurately capture pixel-level grayscale changes in the abnormal leakage area of ​​the image. A modified gas density conversion mapping model transforms the dynamic process of gas leaks in the plugged areas of the compressed air energy storage system chamber into a more easily monitored gas density change. Finally, based on a set warning threshold, the method accurately determines the gas leak monitoring results in the plugged area of ​​the target chamber. This effectively overcomes the shortcomings of existing gas leak monitoring methods in accurately monitoring gas leaks in the plugged areas of compressed air energy storage system chambers, significantly improving the identification accuracy and monitoring stability of gas leaks in the plugged areas of compressed air energy storage chambers.

[0030] According to an embodiment of the present invention, a method for monitoring gas leakage at the plug of a compressed air energy storage system chamber is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] This embodiment provides a method for monitoring gas leakage at the chamber plug of a compressed air energy storage system, which can be used in a monitoring server terminal for compressed air energy storage systems. Figure 1 This is a flowchart of a gas leakage monitoring method for a chamber plug in a compressed air energy storage system according to an embodiment of the present invention, as shown below. Figure 1 As shown, the process includes the following steps: S101, acquires real-time schlieren images of the target chamber plug area of ​​the compressed air energy storage system.

[0032] Schlieren technology is an optical monitoring technique based on the principles of light refraction and interference, used to capture changes in fluid density. It has advantages such as non-contact operation, high sensitivity, and strong real-time performance, and has been widely used in flow field observation in aerospace, fluid mechanics and other fields.

[0033] The real-time schlieren image of the target chamber plug area of ​​the compressed air energy storage system is acquired by a schlieren monitoring system. The schlieren monitoring system includes a schlieren light source, a collimating optical component, a reflector, an imaging optical component, a high-speed camera, and a data processing terminal. The schlieren light source, collimating optical component, reflector, and imaging optical component are arranged sequentially on one side of the compressed air energy storage chamber plug. The high-speed camera is connected to the imaging optical component, and the data processing terminal is communicatively connected to the high-speed camera. The light emitted by the schlieren light source is collimated by the collimating optical component and then illuminates the plug area of ​​the target chamber in parallel. After being reflected by the reflector, it passes through the imaging optical component and finally forms a clear schlieren image of the plug area on the imaging surface of the high-speed camera.

[0034] The schlieren light source can be implemented as a pulsed laser with an output wavelength of 532nm and a pulse width of 10-20ns, which can provide high brightness and high collimation light to ensure clear schlieren images in the complex environment of the target chamber blockage area.

[0035] The high-speed camera has a frame rate of no less than 100fps and a pixel resolution of no less than 1920×1080. It is used to capture the rapid density change process that occurs during gas leaks, ensuring the real-time and accuracy of gas leak monitoring.

[0036] For example, the pulsed laser of the schlieren monitoring system is a solid-state pulsed laser with an output wavelength of 532nm, a pulse width of 15ns, and an output power of 5W; the high-speed camera is a CMOS high-speed camera with a frame rate of 200fps and a pixel resolution of 2560×1440; and the focal length of both the collimating lens and the imaging lens is 500mm.

[0037] S102, based on the real-time schlieren image, a preprocessed schlieren image is obtained using a preset image preprocessing method.

[0038] Image preprocessing methods include dynamic thresholding grayscale algorithm, filtering algorithm, morphological opening operation method and contrast enhancement method, which are used to eliminate various interferences in schlieren images, enhance the leakage weak signal features, and provide high-quality images for subsequent grayscale contrast and density mapping.

[0039] Specifically, to address the fluctuating characteristics of ambient light in the chamber in schlieren images, a dynamic threshold grayscale algorithm is used to convert color images into 8-bit grayscale images, avoiding the loss of weak signals caused by fixed thresholds. To address dust interference that may occur under high-pressure environments, a combined noise reduction algorithm of "median filtering + morphological opening operation" is introduced. First, 3×3 median filtering is used to remove salt-and-pepper noise, and then morphological opening operation is used to eliminate pseudo-interference points formed by tiny dust particles. Finally, an adaptive histogram equalization algorithm is used to enhance the contrast only in areas with dense grayscale distribution in the image, preserving the grayscale stability of the background area and avoiding noise amplification caused by over-enhancement.

[0040] S103. Based on the preprocessed schlieren image and combined with the reference schlieren image of the corresponding chamber plug area, the grayscale difference of the grayscale change abnormal area is obtained by using a two-stage grayscale comparison method; the reference schlieren image includes the schlieren image of the leak-free state after eliminating environmental noise.

[0041] The baseline schlieren image is a multi-frame schlieren image of the plug area acquired by a high-speed camera under stable conditions where the compressed air energy storage chamber is operating normally and there is no gas leakage at the plug. After average filtering to eliminate environmental and equipment noise, the image is used to represent the gray-scale distribution characteristics of the plug area in the compressed air energy storage system under leak-free conditions.

[0042] The two-stage grayscale comparison method includes two grayscale comparison methods: "global coarse comparison" and "local fine matching". The global coarse comparison method uses the global grayscale variance of the preprocessed schlieren image and the reference schlieren image to compare with a preset coarse judgment threshold, quickly filtering out normal frames without leakage and improving monitoring efficiency. The local fine matching comparison method, on the other hand, locks the abnormal area of ​​grayscale change in the image when the global grayscale variance exceeds the coarse judgment threshold, and performs pixel-by-pixel fine matching comparison between the area and the corresponding area of ​​the reference image to accurately capture the subtle grayscale changes caused by leakage.

[0043] Specifically, S103 above includes: Based on the preprocessed schlieren image, combined with the reference schlieren image of the corresponding chamber plug area, the global grayscale variance between the preprocessed schlieren image and the reference schlieren image is obtained; When the global grayscale variance is greater than the coarse judgment threshold, the abnormal grayscale variation region in the preprocessed schlieren image is obtained. When the global grayscale variance is less than or equal to the coarse judgment threshold, the global grayscale variance between the preprocessed schlieren image and the reference schlieren image at the next time step is obtained. Based on the abnormal grayscale change regions in the preprocessed schlieren image and the corresponding regions in the baseline schlieren image, the grayscale difference of the abnormal grayscale change regions is obtained by using a pixel-by-pixel fine matching comparison method.

[0044] For example, the coarse threshold can be set to 8. When the global grayscale variance between the preprocessed schlieren image and the reference schlieren image is less than 8, it is determined that there is no leakage. When the variance between the preprocessed schlieren image and the reference schlieren image is greater than or equal to 8, the abnormal grayscale change region in the preprocessed schlieren image is locked, and the grayscale difference is calculated pixel by pixel.

[0045] S104. Based on the gray-level difference in the abnormal gray-level change region, the gas density change is obtained using the modified gas density conversion mapping model.

[0046] The modified gas density conversion mapping model is a quantitative conversion model of image features and physical quantities optimized based on the principles of schlieren technology, the Gladstone-Dale formula, and the actual calibration results of the schlieren monitoring system. This model integrates the Gladstone-Dale constant, the light propagation path length, and the modified gray-scale-deflection angle conversion coefficient related to gas type and light wavelength, as well as actual working condition parameters, to accurately convert gray-scale differences into gas density changes.

[0047] An exemplary modified gas density transformation mapping model includes: , in, This indicates the change in gas density; Indicates the difference in gray levels of the image; This represents the corrected grayscale-to-angle conversion coefficient; This represents the Gladstone-Dale constant, which is determined based on the type of gas in the chamber plug area and the wavelength of the schlieren light source.

[0048] The correction process for the grayscale-deflection angle conversion coefficient includes: , in, Indicates the angle of light deflection (rad); Indicates the refractive index of a gas; This represents the path length (m) of light propagation in a gaseous medium. This represents the refractive index gradient (1 / m) along the direction perpendicular to the propagation of light.

[0049] At the same time, the refractive index and density of the gas satisfy the Gladstone-Dale formula: , in, Indicates the refractive index of a gas; This represents the Gladstone-Dale constant (m³ / kg), which is related to the type of gas and the wavelength of light. This indicates the gas density (kg / m³).

[0050] Combining the above two equations, we can obtain: , To address the density calculation errors caused by traditional linear mapping, a nonlinear mapping model established during the system calibration phase is used to accurately convert grayscale differences into the gas density variation distribution in the plug region. The core calculation relationships are as follows: , In the formula, Represents the grayscale difference in an image (unitless); This represents the corrected grayscale-to-deflection angle conversion coefficient (determined by system calibration, rad). - ¹).

[0051] By utilizing the correspondence between light deflection and gas density change, the gray values ​​in the gray-scale difference image are converted into corresponding gas density changes, generating a cloud map of gas density change distribution in the blockage area.

[0052] S105, based on the change in gas density and combined with the early warning threshold of the target chamber, obtain the gas leakage monitoring results of the plug area of ​​the target chamber.

[0053] The warning threshold for the target chamber is based on the design pressure of the target chamber, the allowable leakage of the plug material, and the operational safety specifications. It is a graded judgment value for gas density change established through experimental calibration, which corresponds to the judgment threshold for minor, moderate, and severe leaks, respectively.

[0054] This embodiment provides a method for monitoring gas leakage in the plugged area of ​​a compressed air energy storage system chamber. It utilizes non-contact schlieren image acquisition, combined with image preprocessing to offset the influence of complex environmental factors such as chamber light fluctuations and dust interference. A two-stage grayscale comparison method is then used to accurately capture pixel-level grayscale changes in the leakage anomaly area of ​​the image. A corrected gas density conversion mapping model transforms the dynamic process of gas leakage in the plugged area of ​​the compressed air energy storage system chamber into a more easily monitored gas density change. Finally, based on a set warning threshold, the method accurately determines the gas leakage monitoring result in the plugged area of ​​the target chamber. This effectively overcomes the shortcomings of related gas leakage monitoring methods, which struggle to accurately monitor gas leakage in the plugged area of ​​compressed air energy storage system chambers, significantly improving the identification accuracy and monitoring stability of gas leakage in the plugged area of ​​compressed air energy storage chambers.

[0055] This embodiment provides a method for monitoring gas leakage at the chamber plug of a compressed air energy storage system, which can be used in a monitoring server terminal for compressed air energy storage systems. Figure 2 This is a flowchart of a gas leakage monitoring method for a chamber plug in a compressed air energy storage system according to an embodiment of the present invention, as shown below. Figure 2 As shown, the process includes the following steps: S201 acquires real-time schlieren images of the target chamber plug area of ​​the compressed air energy storage system. For details, please refer to [link to documentation]. Figure 1 S101 of the illustrated embodiment will not be described again here.

[0056] S202: Based on the real-time schlieren image, a preprocessed schlieren image is obtained using a preset image preprocessing method.

[0057] Specifically, S202 above includes: S2021, based on real-time schlieren images, grayscale images are obtained by using a dynamic threshold grayscale conversion algorithm to perform grayscale conversion. S2022, based on grayscale images, uses filtering algorithms and morphological opening operations to obtain denoised schlieren images; S2023: Based on the densely distributed gray areas in the denoised schlieren image, a contrast enhancement method is used to process the image to obtain a preprocessed schlieren image.

[0058] To address the complex operating environment of compressed air energy storage chambers—characterized by high pressure, high humidity, fluctuating light, and dust interference—in the acquired real-time schlieren images, a dynamic threshold grayscale algorithm is first used to convert color images into grayscale images, eliminating the loss of weak leakage signals that can occur with fixed threshold grayscale conversion. Then, a combination of filtering algorithms and morphological opening operations is used for noise reduction to precisely remove salt-and-pepper noise and pseudo-interference points formed by tiny dust particles, significantly reducing the impact of chamber environment interference on image quality. Finally, contrast enhancement is applied only to areas with dense grayscale distribution in the denoised image. This targeted enhancement of contrast in areas with weak leakage signals highlights leakage-related image features while preserving grayscale stability in the background area, avoiding noise amplification caused by global contrast enhancement. This approach effectively overcomes various interferences from the complex chamber environment on schlieren images while maximizing the preservation and enhancement of effective leakage-related image features.

[0059] For example, S2023 above includes: Based on the densely distributed gray areas in the denoised schlieren image, an adaptive histogram equalization method is used to enhance contrast, resulting in a gray image that retains the background area, which is then used as the preprocessed schlieren image.

[0060] Contrast enhancement processing is performed on the dense gray-scale distribution areas in the denoised schlieren image. This effectively improves the gray-scale contrast of the weak signal area caused by gas leakage in the plug area and highlights the image features related to the leakage. At the same time, it can preserve the gray-scale stability of the image background area to the greatest extent and avoid the background noise amplification problem caused by global enhancement. From the perspective of image feature optimization, it further reduces the interference of the complex environment of the chamber on monitoring and analysis.

[0061] S203, based on the preprocessed schlieren image and combined with the baseline schlieren image of the corresponding chamber plug area, uses a two-stage grayscale comparison method to obtain the grayscale difference value of the area with abnormal grayscale changes; the baseline schlieren image includes a schlieren image of the leak-free state after eliminating environmental noise. For details, please refer to [link to relevant documentation]. Figure 1 S103 of the illustrated embodiment will not be described again here.

[0062] S204, based on the gray-level difference in areas of abnormal gray-level change, uses a modified gas density conversion mapping model to obtain the gas density change. For details, please refer to [link to relevant documentation]. Figure 1 S104 of the illustrated embodiment will not be described again here.

[0063] S205, based on the change in gas density and combined with the warning threshold of the target chamber, yields the gas leakage monitoring results in the plugged area of ​​the target chamber. For details, please refer to [link to relevant documentation]. Figure 1 S105 of the illustrated embodiment will not be described again here.

[0064] This embodiment provides a method for monitoring gas leakage in the plugged area of ​​a compressed air energy storage system chamber. It utilizes non-contact schlieren image acquisition, combined with image preprocessing to offset the influence of complex environmental factors such as chamber light fluctuations and dust interference. A two-stage grayscale comparison method is then used to accurately capture pixel-level grayscale changes in the leakage anomaly area of ​​the image. A corrected gas density conversion mapping model transforms the dynamic process of gas leakage in the plugged area of ​​the compressed air energy storage system chamber into a more easily monitored gas density change. Finally, based on a set warning threshold, the method accurately determines the gas leakage monitoring result in the plugged area of ​​the target chamber. This effectively overcomes the shortcomings of related gas leakage monitoring methods, which struggle to accurately monitor gas leakage in the plugged area of ​​compressed air energy storage system chambers, significantly improving the identification accuracy and monitoring stability of gas leakage in the plugged area of ​​compressed air energy storage chambers.

[0065] This embodiment provides a method for monitoring gas leakage at the chamber plug of a compressed air energy storage system, which can be used in a monitoring server terminal for compressed air energy storage systems. Figure 3 This is a flowchart of a gas leakage monitoring method for a chamber plug in a compressed air energy storage system according to an embodiment of the present invention, as shown below. Figure 3 As shown, the process includes the following steps: S301 acquires real-time schlieren images of the target chamber plug area of ​​the compressed air energy storage system. For details, please refer to [link to documentation]. Figure 1 S101 of the illustrated embodiment will not be described again here.

[0066] S302, based on the real-time schlieren image, uses a preset image preprocessing method to obtain a preprocessed schlieren image. For details, please refer to [link to details]. Figure 1 S102 of the illustrated embodiment will not be described again here.

[0067] S303, based on the preprocessed schlieren image and combined with the reference schlieren image of the corresponding chamber plug area, uses a two-stage grayscale comparison method to obtain the grayscale difference value of the area with abnormal grayscale changes; the reference schlieren image includes the schlieren image of the leak-free state after eliminating environmental noise. For details, please refer to... Figure 1 S103 of the illustrated embodiment will not be described again here.

[0068] S304, based on the grayscale difference in areas of abnormal grayscale change, uses a modified gas density conversion mapping model to obtain the gas density change. For details, please refer to [link to relevant documentation]. Figure 1 S104 of the illustrated embodiment will not be described again here.

[0069] S305, based on the change in gas density and combined with the early warning threshold of the target chamber, obtains the gas leakage monitoring results of the plug area of ​​the target chamber.

[0070] Specifically, the aforementioned S305 includes: When the change in gas density is greater than or equal to the first threshold and less than the second threshold, the gas leakage monitoring result in the plug area of ​​the target chamber is a minor leak. When the change in gas density is greater than or equal to the second threshold and less than the third threshold, the gas leakage monitoring result in the plug area of ​​the target chamber is a moderate leakage. When the change in gas density exceeds the third threshold, the gas leakage monitoring result in the plug area of ​​the target chamber is a serious leak.

[0071] By accurately comparing the first, second, and third thresholds with changes in gas density, the leakage level can be quantitatively determined. Through clear numerical range divisions, the gas leakage monitoring results in the corresponding ranges are classified as minor, moderate, and severe leaks, forming a standardized and quantifiable leakage level determination rule. This rule can accurately match the actual sealing state of the plug with the degree of leakage development. It not only provides clear and intuitive gas leakage monitoring results but also provides a clear and unified basis for triggering subsequent tiered early warning and response mechanisms, allowing different levels of leakage to be matched with differentiated early warning and handling strategies.

[0072] For example, the first threshold Δρ1 is 0.02 kg / m³, the second threshold Δρ2 is 0.05 kg / m³, and the third threshold Δρ3 is 0.1 kg / m³.

[0073] S306 When the change in gas density is greater than or equal to the first threshold, the outline, center coordinates, area and diffusion rate of the leak area are obtained by using a connected component analysis algorithm and the mapping relationship between the camera's pixel coordinates and the physical size of the plug area.

[0074] After determining that the gas density change has reached the first threshold for leak detection, the contour of the abnormal density change area is extracted simultaneously using a connected component analysis algorithm. Combined with the mapping relationship between the camera's pixel coordinates and the physical size of the plug area, the contour, center coordinates, area, and diffusion rate of the leak area are accurately calculated and quantitatively characterized. This not only completes the determination of the leak level, but also achieves comprehensive and accurate positioning and dynamic monitoring of the leak location, range, and diffusion trend, providing accurate and comprehensive spatial and dynamic data support for the formulation of targeted emergency response and maintenance plans.

[0075] Specifically, the density change distribution cloud map is compared with the first, second, and third thresholds. The outline of the abnormal region is extracted by the connected component analysis algorithm. Combined with the mapping relationship between pixel coordinates and the physical size of the plug, the center coordinates, area, and diffusion rate of the leakage region are calculated.

[0076] Simultaneously triggering corresponding early warning mechanisms includes: when the gas leakage monitoring result of the target chamber blockage area is a minor leak, only a terminal pop-up window is recorded; when the gas leakage monitoring result of the target chamber blockage area is a moderate leak, an audible and visual early warning is triggered and pushed to the operation and maintenance terminal; when the gas leakage monitoring result of the target chamber blockage area is a serious leak, the main control unit of the energy storage system is additionally linked to recommend pressure reduction, and all information (time, location, level, image, etc.) is stored in the database for traceability.

[0077] When a leak is detected, the audible and visual warning device is immediately triggered to issue a warning signal. At the same time, the time of the leak, the coordinates of the leak location, the degree of the leak (maximum density change), and the corresponding real-time schlieren image and density change distribution cloud map are stored in the database and displayed on the monitor in real time, so that staff can understand the leak situation in a timely manner and carry out maintenance.

[0078] This embodiment provides a method for monitoring gas leakage in the plugged area of ​​a compressed air energy storage system chamber. It utilizes non-contact schlieren image acquisition, combined with image preprocessing to offset the influence of complex environmental factors such as chamber light fluctuations and dust interference. A two-stage grayscale comparison method is then used to accurately capture pixel-level grayscale changes in the leakage anomaly area of ​​the image. A corrected gas density conversion mapping model transforms the dynamic process of gas leakage in the plugged area of ​​the compressed air energy storage system chamber into a more easily monitored gas density change. Finally, based on a set warning threshold, the method accurately determines the gas leakage monitoring result in the plugged area of ​​the target chamber. This effectively overcomes the shortcomings of related gas leakage monitoring methods, which struggle to accurately monitor gas leakage in the plugged area of ​​compressed air energy storage system chambers, significantly improving the identification accuracy and monitoring stability of gas leakage in the plugged area of ​​compressed air energy storage chambers.

[0079] This embodiment also provides a gas leakage monitoring device for the chamber plug of a compressed air energy storage system. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0080] This embodiment provides a gas leakage monitoring device for the chamber plug of a compressed air energy storage system, such as... Figure 4 As shown, it includes: Image acquisition module 410 is used to acquire real-time schlieren images of the target chamber plug area of ​​the compressed air energy storage system; The image preprocessing module 420 is used to obtain a preprocessed schlieren image based on the real-time schlieren image using a preset image preprocessing method; The abnormal region identification module 430 is used to obtain the grayscale difference of the abnormal grayscale region based on the preprocessed schlieren image and the reference schlieren image of the corresponding chamber plug region using a two-stage grayscale comparison method; the reference schlieren image includes the schlieren image of the leak-free state after eliminating environmental noise. The data conversion module 440 is used to obtain the gas density change based on the gray level difference in the gray level change abnormal area using the modified gas density conversion mapping model; The result generation module 450 is used to obtain the gas leakage monitoring results of the plug area of ​​the target chamber based on the change in gas density and the early warning threshold of the target chamber.

[0081] In some alternative implementations, the image preprocessing module 420 includes: The grayscale conversion unit is used to convert grayscale based on real-time schlieren images using a dynamic threshold grayscale algorithm to obtain grayscale images; The noise reduction processing unit is used to obtain a denoised schlieren image based on a grayscale image by using filtering algorithms and morphological opening operations. The contrast enhancement unit is used to process areas with dense grayscale distribution in the denoised schlieren image using a contrast enhancement method to obtain a preprocessed schlieren image.

[0082] In some alternative implementations, the contrast enhancement unit is specifically used for: Based on the densely distributed gray areas in the denoised schlieren image, an adaptive histogram equalization method is used to enhance contrast, resulting in a gray image that retains the background area, which is then used as the preprocessed schlieren image.

[0083] In some optional implementations, the abnormal region identification module 430 is specifically used for: Based on the preprocessed schlieren image, combined with the reference schlieren image of the corresponding chamber plug area, the global grayscale variance between the preprocessed schlieren image and the reference schlieren image is obtained; When the global grayscale variance is greater than the coarse judgment threshold, the abnormal grayscale variation region in the preprocessed schlieren image is obtained. When the global grayscale variance is less than or equal to the coarse judgment threshold, the global grayscale variance between the preprocessed schlieren image and the reference schlieren image at the next time step is obtained. Based on the abnormal grayscale change regions in the preprocessed schlieren image and the corresponding regions in the baseline schlieren image, the grayscale difference of the abnormal grayscale change regions is obtained by using a pixel-by-pixel fine matching comparison method.

[0084] In some alternative implementations, the modified gas density conversion mapping model includes: , in, This indicates the change in gas density; Indicates the difference in gray levels of the image; This represents the corrected grayscale-to-angle conversion coefficient; This represents the Gladstone-Dale constant, which is determined based on the type of gas in the chamber plug area and the wavelength of the schlieren light source.

[0085] In some optional implementations, the warning threshold for the target chamber includes a first threshold, a second threshold, and a third threshold; the result generation module 450 includes: The first result unit is used to determine that the gas leakage monitoring result of the target chamber plug area is a minor leak when the gas density change is greater than or equal to the first threshold and less than the second threshold. The second result unit is used to determine that the gas leakage monitoring result of the target chamber plug area is a moderate leakage when the gas density change is greater than or equal to the second threshold and less than the third threshold. The third result unit is used to determine that the gas leakage monitoring result in the plug area of ​​the target chamber is a serious leak when the gas density change is greater than the third threshold.

[0086] In some alternative implementations, it also includes: The region filtering module is used to obtain the outline, center coordinates, area, and diffusion rate of the leak area by using a connected component analysis algorithm and the mapping relationship between the camera's pixel coordinates and the physical size of the plug area when the gas density change is greater than or equal to a first threshold.

[0087] The compressed air energy storage system chamber plug gas leakage monitoring device provided in this embodiment of the invention can execute the compressed air energy storage system chamber plug gas leakage monitoring method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0088] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0089] The following is a detailed reference. Figure 5The diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from memory 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the electronic device. The processor 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0090] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0091] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a memory 508, or installed from a ROM 502. When the computer program is executed by the processor 501, it performs the functions defined in the compressed air energy storage system chamber plug gas leakage monitoring method of the embodiments of the present invention.

[0092] Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0093] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that the computer, processor, microprocessor controller, or programmable hardware includes storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the compressed air energy storage system chamber plug gas leakage monitoring method shown in the above embodiments is implemented.

[0094] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0095] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for monitoring gas leakage at the chamber plug of a compressed air energy storage system, characterized in that, The method includes: Real-time schlieren images of the target chamber plug area of ​​the compressed air energy storage system were acquired; Based on the real-time schlieren image, a preprocessed schlieren image is obtained using a preset image preprocessing method; Based on the preprocessed schlieren image, combined with the reference schlieren image of the corresponding chamber plug area, the grayscale difference value of the grayscale change abnormal area is obtained by using a two-stage grayscale comparison method; the reference schlieren image includes the schlieren image in a leak-free state after eliminating environmental noise. Based on the gray-level difference in the gray-level change anomaly region, the gas density change is obtained using the modified gas density conversion mapping model. Based on the gas density change and the early warning threshold of the target chamber, the gas leakage monitoring results of the plugged area of ​​the target chamber are obtained.

2. The method according to claim 1, characterized in that, The step of obtaining a preprocessed schlieren image based on the real-time schlieren image using a preset image preprocessing method includes: Based on the real-time schlieren image, a grayscale image is obtained by performing grayscale conversion using a dynamic threshold grayscale algorithm. Based on the grayscale image, a denoised schlieren image is obtained by using a filtering algorithm and a morphological opening operation method. Based on the densely gray-scale regions in the denoised schlieren image, a contrast enhancement method is used to process the image to obtain a preprocessed schlieren image.

3. The method according to claim 2, characterized in that, The preprocessed schlieren image is obtained by processing the densely gray-level regions in the denoised schlieren image using a contrast enhancement method, including: Based on the densely distributed grayscale regions in the denoised schlieren image, an adaptive histogram equalization method is used to enhance contrast, resulting in a grayscale image that retains the background region, which is then used as the preprocessed schlieren image.

4. The method according to claim 1, characterized in that, Based on the preprocessed schlieren image, combined with the reference schlieren image of the corresponding chamber plug area, a two-stage grayscale comparison method is used to obtain the grayscale difference value of the area with abnormal grayscale changes, including: Based on the preprocessed schlieren image, combined with the reference schlieren image of the corresponding chamber plug area, the global grayscale variance between the preprocessed schlieren image and the reference schlieren image is obtained; When the global grayscale variance is greater than the coarse judgment threshold, the abnormal grayscale change region in the preprocessed schlieren image is obtained; when the global grayscale variance is less than or equal to the coarse judgment threshold, the global grayscale variance between the preprocessed schlieren image and the reference schlieren image at the next time step is obtained. Based on the abnormal grayscale regions in the preprocessed schlieren image and the corresponding regions in the reference schlieren image, the grayscale difference of the abnormal grayscale regions is obtained using a pixel-by-pixel fine matching comparison method.

5. The method according to claim 1, characterized in that, The corrected gas density conversion mapping model includes: ， in, This indicates the change in gas density; Indicates the difference in gray levels of the image; This represents the corrected grayscale-to-angle conversion coefficient; This represents the Gladstone-Dale constant, which is determined based on the type of gas in the chamber plug area and the wavelength of the schlieren light source.

6. The method according to claim 1, characterized in that, The warning threshold for the target chamber includes a first threshold, a second threshold, and a third threshold; the gas leakage monitoring results for the plugged area of ​​the target chamber, based on the gas density change and combined with the warning threshold of the target chamber, include: When the change in gas density is greater than or equal to the first threshold and less than the second threshold, the gas leakage monitoring result of the target chamber plug area is a minor leak. When the change in gas density is greater than or equal to the second threshold and less than the third threshold, the gas leakage monitoring result of the target chamber plug area is a moderate leakage. When the change in gas density exceeds the third threshold, the gas leakage monitoring result in the plug area of ​​the target chamber is a serious leak.

7. The method according to claim 6, characterized in that, Also includes: When the change in gas density is greater than or equal to a first threshold, the outline, center coordinates, area, and diffusion rate of the leak area are obtained by using a connected component analysis algorithm and the mapping relationship between the camera's pixel coordinates and the physical size of the plug area.

8. A gas leakage monitoring device for a chamber plug in a compressed air energy storage system, characterized in that, The device includes: The image acquisition module is used to acquire real-time schlieren images of the target chamber plug area of ​​the compressed air energy storage system; The image preprocessing module is used to obtain a preprocessed schlieren image based on the real-time schlieren image using a preset image preprocessing method; An abnormal region identification module is used to obtain the grayscale difference of the abnormal grayscale region based on the preprocessed schlieren image and the reference schlieren image of the corresponding chamber plug region using a two-stage grayscale comparison method; the reference schlieren image includes a schlieren image in a leak-free state after eliminating environmental noise. The data conversion module is used to obtain the gas density change based on the gray level difference in the gray level change abnormal area using the modified gas density conversion mapping model; The result generation module is used to obtain the gas leakage monitoring results of the plugged area of ​​the target chamber based on the gas density change and the early warning threshold of the target chamber.

9. An electronic device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the gas leakage monitoring method for the chamber plug of the compressed air energy storage system as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the gas leakage monitoring method for the chamber plug of the compressed air energy storage system according to any one of claims 1 to 7.

Images