Method, device and equipment for detecting gas leakage of natural gas inflation arm and storage medium

Abstract

The invention relates to the technical field of natural gas leakage detection, and discloses a method, device and equipment for detecting gas leakage of a natural gas inflation arm and a storage medium, and the method for detecting gas leakage of the natural gas inflation arm comprises the steps: collecting a visible light image and an infrared light image of a pipeline connection area of the inflation arm; identifying the morphological characteristics of the first image to obtain a first morphological detection result; extracting a first region of which the temperature is lower than a preset threshold value in the second image, performing thresholding processing on the second image, calculating an area proportion of the first region relative to the second image to obtain first proportion data, and comparing the first proportion data with a preset proportion data range; if it is judged that the first form detection result is smog and the first proportion data is within a preset proportion data range, it is judged that gas leakage occurs in the inflation arm pipeline connection area, and a leakage warning prompt is given out. According to the technical scheme, whether gas leaks or not can be detected in time, an alarm prompt is given out, and the detection accuracy is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of natural gas leakage detection, and particularly relates to a method and device for detecting gas leakage of a natural gas inflation arm, equipment and a storage medium. BACKGROUND

[0002] In the process of natural gas storage and transportation, the inflation arm as a key connecting device, the pipeline connection is prone to gas leakage due to sealing failure and other reasons. In the prior art, artificial inspection is usually used to identify whether gas leakage occurs. Artificial inspection is inefficient, and cannot identify trace gas leakage with naked eyes, cannot discover gas leakage in time and process it, and is not conducive to the safety of storage and transportation work. SUMMARY

[0003] The present application provides a method, device, equipment and storage medium for detecting gas leakage of a natural gas inflation arm, which can detect whether gas leakage of the inflation arm occurs in time and issue an alarm prompt, and improve the detection accuracy.

[0004] In the first aspect, the present application provides a method for detecting gas leakage of a natural gas inflation arm, comprising: collecting images of a pipeline connection area of the inflation arm to obtain first and second images with at least partially overlapping areas, the first image being a visible light image of the pipeline connection area of the inflation arm, and the second image being an infrared light image of the pipeline connection area of the inflation arm; identifying morphological features of the first image by a deep learning target detection algorithm to obtain a first morphological detection result; extracting a first area with a temperature lower than a preset threshold from the second image, and performing thresholding processing on the second image to calculate an area ratio of the first area relative to the second image, obtain first proportion data, and compare the first proportion data with a preset proportion data range, the preset proportion data range being a preset area ratio interval of the first area when gas leakage occurs; if the first morphological detection result is judged to be smoke, and the first proportion data is within the preset proportion data range, it is judged that gas leakage occurs in the pipeline connection area of the inflation arm, and a leakage alarm prompt is issued. The technical scheme of the present application acquires a first image and a second image of the pipeline connection area of the inflatable arm, the first image is a visible light image of the pipeline connection area of the inflatable arm, the second image is an infrared light image of the pipeline connection area of the inflatable arm, the morphological features of the first image are identified by a deep learning target detection algorithm to obtain a first morphological detection result, a first area with a temperature lower than a preset threshold in the second image is extracted, the second image is thresholded, the area ratio of the first area relative to the second image is calculated to obtain first proportion data, and the first proportion data is compared with a preset proportion data range, if the first morphological detection result is judged to be smoke-shaped and the first proportion data is within the preset proportion data range, it is judged that gas leakage occurs in the pipeline connection area of the inflatable arm, and a leakage warning prompt is issued. By combining the morphological feature recognition of the visible light image with the temperature anomaly analysis of the infrared light image, the limitations of single modal detection are avoided, which is conducive to improving the accuracy of detecting gas leakage. By calculating the area ratio of the first area relative to the second image and comparing the first proportion data with the preset proportion data range to determine whether leakage occurs, the calculation method is simplified and the calculation amount is reduced, which can timely detect whether the inflatable arm gas leaks and issue an alarm prompt, facilitating operators to timely discover and repair.

[0005] According to the foregoing embodiment of the first aspect of the present application, the identification of the morphological features of the first image by the deep learning target detection algorithm includes: training a visible light image sample containing smoke-shaped leakage features according to a deep learning algorithm to obtain a target detection model and a preset smoke-shaped gas leakage feature; identifying and comparing the morphological features of the first image by the target detection model to obtain a first morphological detection result; comparing the first morphological detection result with the preset smoke-shaped gas leakage feature to determine whether the first morphological detection result is consistent with the preset smoke-shaped gas leakage feature, and if the first morphological detection result is consistent with the preset smoke-shaped gas leakage feature, it is determined that gas leakage occurs in the pipeline connection area of the inflatable arm.

[0006] According to the foregoing embodiment of the first aspect of the present application, the step of thresholding the second image further comprises: obtaining the proportion data when the gas is not leaked, comprising: obtaining a third image of the pipeline and the surrounding area when the pipeline is normally inflated and the gas is not leaked, the third image comprising pipeline infrared image information and surrounding area infrared image information, the temperature of the pipeline being lower than the temperature of the surrounding area; extracting the pipeline infrared image information and marking it as a first pixel color, and extracting the surrounding area infrared image information and marking it as a second pixel color; thresholding the third image to obtain a pipeline pixel pattern comprising the first pixel color and a surrounding area pixel pattern comprising the second pixel color, the set of the pipeline pixel pattern and the surrounding area pixel pattern being a third image pixel pattern; and calculating the area proportion of the pipeline pixel pattern relative to the third image pixel pattern to obtain the second proportion data when the gas is not leaked.

[0007] According to the foregoing embodiment of the first aspect of the present application, the step of extracting a first region in the second image whose temperature is lower than a preset threshold value, thresholding the second image, calculating the area proportion of the first region relative to the second image to obtain the first proportion data comprises: extracting the first region and marking it as a first pixel color; extracting a second region in the second image whose temperature is higher than a preset threshold value and marking it as a second pixel color; thresholding the second image to obtain a first region pixel pattern comprising the first pixel color and a second region pixel pattern comprising the second pixel color, the set of the first region pixel pattern and the second region pixel pattern being a second image pixel pattern, wherein the first region pixel pattern comprises a pipeline pixel pattern and the second region pixel pattern comprises a surrounding area pixel pattern; and calculating the area proportion of the first region pixel pattern relative to the second image pixel pattern to obtain the first proportion data.

[0008] According to the foregoing embodiment of the first aspect of the present application, the minimum value of the preset proportion data range is greater than the second proportion data; if there is a difference between the first proportion data and the second proportion data and the first proportion data is greater than the second proportion data, it is determined that the gas leakage occurs in the inflation arm pipeline connection area.

[0009] According to the foregoing embodiment of the first aspect of the present application, after the step of determining that the gas leakage occurs in the inflation arm pipeline connection area, the method further comprises: fusing the first image and the thresholded second image to obtain a fusion image containing visual morphological features and temperature information of the leakage area, and transmitting and saving the fusion image to a server.

[0010] In a second aspect, an embodiment of the present application provides a device for detecting gas leakage of a natural gas inflatable arm, comprising: an image acquisition module, a first image processing module, a second image processing module, and an alarm module. The image acquisition module is configured to acquire an image of a pipeline connection area of the inflatable arm. The first image processing module is configured to identify morphological features of the first image by using a deep learning target detection algorithm. The second image processing module is configured to extract a first area in the second image where the temperature is lower than a preset threshold, perform thresholding processing on the second image, calculate an area ratio of the first area relative to the second image, obtain first ratio data, and compare the first ratio data with a preset ratio data range. The alarm module is configured to determine whether the first morphological detection result is a smoke-like area and whether the first ratio data is within the preset ratio data range, and to issue a leakage alarm prompt.

[0011] According to the foregoing embodiment of the second aspect of the present application, the alarm module comprises a first prompt module and a second prompt module, the first prompt module is configured to generate a voice broadcast prompt, and the second prompt module is configured to issue a buzzer sound prompt and / or generate a warning light prompt.

[0012] In a third aspect, an embodiment of the present application provides a device for detecting gas leakage of a natural gas inflatable arm, comprising: a memory and at least one processor, the memory storing instructions; and the at least one processor invoking the instructions in the memory to enable the device to perform the method for detecting gas leakage of a natural gas inflatable arm according to any one of the foregoing embodiments of the first aspect of the present application.

[0013] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, the computer readable storage medium storing instructions, the instructions being executed by a processor to implement the method for detecting gas leakage of a natural gas inflatable arm according to any one of the foregoing embodiments of the first aspect of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, brief descriptions will be given below to the drawings needed to be used in the embodiments or prior art descriptions. Obviously, the drawings described below are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without any creative effort based on the drawings shown.

[0015] Figure 1 A step flowchart of an embodiment of the method for detecting gas leakage of a natural gas inflatable arm of the present application; Figure 2 A step flowchart of an embodiment of the method for detecting gas leakage of a natural gas inflatable arm of the present application; Figure 3The third image schematic diagram obtained when the gas is not leaked in the method for detecting gas leakage of the natural gas inflatable arm according to an embodiment of the present application; Figure 4 The step flow schematic diagram of obtaining the proportional data when the gas is not leaked in the method for detecting gas leakage of the natural gas inflatable arm according to an embodiment of the present application; Figure 5 The step flow schematic diagram of obtaining the first proportional data in the method for detecting gas leakage of the natural gas inflatable arm according to an embodiment of the present application; Figure 6 The schematic diagram of the device for detecting gas leakage of the natural gas inflatable arm according to an embodiment of the present application; Figure 7 The schematic diagram of the device for detecting gas leakage of the natural gas inflatable arm according to an embodiment of the present application.

[0016] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0017] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.

[0018] It should be noted that all the directionality indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present application are only used to explain the relative position relationship, movement condition, etc. between the components in a certain posture (as shown in the drawings). If the certain posture changes, the directionality indications also change accordingly.

[0019] In addition, the descriptions of "first", "second" and the like in the present application are only for the purpose of description, and cannot be understood as indicating or implying the relative importance of the indicated technical features or implicitly indicating the number of the indicated technical features. Therefore, the features limited by "first", "second" can explicitly or implicitly include at least one of the features. In addition, the technical solutions of each embodiment can be combined with each other, but it must be based on the fact that a person skilled in the art can realize it. When the combination of technical solutions appears contradictory or unachievable, it should be considered that the combination of technical solutions does not exist, and is not within the protection scope of the present application.

[0020] The embodiments of the present application provide a method, device, equipment and storage medium for detecting gas leakage of a natural gas inflatable arm, which can be beneficial to timely detect whether the gas of the inflatable arm is leaked and issue an alarm prompt, and improve the detection accuracy.

[0021] As Figure 1 shown, the embodiment of the present application provides a method for detecting gas leakage of natural gas inflatable arm, comprising steps S100 to S400.

[0022] In step S100, images of the inflatable arm pipeline connection area are collected to obtain first and second images with at least partially overlapping regions, and at least 80% of the regions are overlapping regions. The first image is a visible light image of the inflatable arm pipeline connection area, and the second image is an infrared light image of the inflatable arm pipeline connection area. By combining the morphological feature recognition of the visible light image with the temperature anomaly analysis of the infrared light image, the limitations of single modal detection are avoided. If only visible light images are used for detection, false positives are easily caused by environmental smoke, dust and other interference. If only infrared light images are used for detection, low-temperature objects (such as ice blocks) are easily misjudged as leakage sources. By combining the morphological feature recognition of the visible light image with the temperature anomaly analysis of the infrared light image, the accuracy of the detection can be improved.

[0023] In step S200, the morphological features of the first image are recognized by a deep learning target detection algorithm to obtain a first morphological detection result. In one embodiment, the morphological features of the first image can include a pre-processing step, which includes image denoising, histogram equalization, image enhancement, etc., to improve the detection accuracy of the deep learning model.

[0024] Further, the YOLOv5 improved model can be used for target detection of the first image, and a detection module for smoke features is added to recognize the smoke-like morphological features, which helps to improve the detection accuracy.

[0025] The detection result is compared with a preset smoke feature library (containing leakage pattern templates under different concentrations and flow rates) to generate the first morphological detection result.

[0026] In step S300, a first region with a temperature lower than a preset threshold in the second image is extracted, and the second image is thresholded to calculate the area ratio of the first region relative to the second image to obtain first ratio data. The first ratio data is compared with a preset ratio data range, which is a preset area ratio interval of the first region when gas leakage occurs. In one embodiment, the thresholding of the second image further includes filtering and background modeling of the second image to remove false positives caused by environmental temperature interference and equipment body automatic heating.

[0027] In step S400, if the first morphological detection result is smoke-like and the first ratio data is within the preset ratio data range, it is determined that gas leakage occurs in the inflatable arm pipeline connection area, and a leakage warning prompt is issued. The technical scheme of the present application acquires a first image and a second image of the pipeline connection area of the inflatable arm, the first image is a visible light image of the pipeline connection area of the inflatable arm, the second image is an infrared light image of the pipeline connection area of the inflatable arm, identifies the morphological features of the first image through a deep learning target detection algorithm, obtains a first morphological detection result, extracts a first area in the second image where the temperature is lower than a preset threshold, and performs thresholding processing on the second image, calculates the area ratio of the first area relative to the second image, obtains first proportion data, and compares the first proportion data with a preset proportion data range, if the first morphological detection result is judged to be smoke-shaped, and the first proportion data is within the preset proportion data range, it is judged that gas leakage occurs in the pipeline connection area of the inflatable arm, and a leakage warning prompt is issued. By combining the morphological feature recognition of the visible light image with the temperature anomaly analysis of the infrared light image, the limitations of single modal detection are avoided, which is beneficial to improve the accuracy of detecting gas leakage. By calculating the area ratio of the first area relative to the second image, and comparing the first proportion data with the preset proportion data range to judge whether leakage occurs, the calculation method is simplified and the calculation amount is reduced, which can timely detect whether the inflatable arm gas leaks and issue an alarm prompt, facilitating the operator to find and repair in time.

[0028] As shown in Figure 2 The step S200 of identifying the morphological features of the first image through the deep learning target detection algorithm includes steps S210 to S230.

[0029] In step S210, according to the deep learning algorithm, visible light image samples containing smoke-shaped leakage features are trained to obtain a target detection model and a preset smoke-shaped gas leakage feature.

[0030] In step S220, the morphological features of the first image are identified and compared through the target detection model to obtain a first morphological detection result.

[0031] In step S230, the first morphological detection result is compared with the preset smoke-shaped gas leakage feature to determine whether the first morphological detection result is consistent with the preset smoke-shaped gas leakage feature, if the first morphological detection result is consistent with the preset smoke-shaped gas leakage feature, it is judged that gas leakage occurs in the pipeline connection area of the inflatable arm.

[0032] As shown in Figure 3 Before the step S300 of thresholding processing the second image, it also includes obtaining proportion data when the gas is not leaked, including steps S311 to S314.

[0033] In step S311, a third image of the pipeline and its surrounding area is acquired when the pipeline is being filled normally and there is no gas leakage. The third image includes infrared light image information of the pipeline and infrared light image information of the surrounding area. The temperature of the pipeline is lower than that of the surrounding area. Since the temperature of liquefied natural gas is below 0°C, the inflation arm and pipeline and other facilities will also be below 0°C during filling. Therefore, when the pipeline is being filled normally and there is no gas leakage, the infrared light image of the pipeline is different in color from the infrared light image of the surrounding area.

[0034] In step S312, the infrared light image information of the pipeline is extracted and marked as the first pixel color, and the infrared light image information of the surrounding area is extracted and marked as the second pixel color.

[0035] In step S313, the third image is thresholded to obtain a pipe pixel pattern including the color of the first pixel and a surrounding area pixel pattern including the color of the second pixel. The set of the pipe pixel pattern and the surrounding area pixel pattern is the pixel pattern of the third image.

[0036] In step S314, the area ratio of the pipe pixel pattern to the third image pixel pattern is calculated to obtain the second ratio data when there is no gas leakage.

[0037] Specifically, because the temperature of liquefied natural gas is below 0°C, the filling arms and pipelines will also be below 0°C during filling. In one implementation, such as... Figure 3 As shown, by adjusting the settings of the infrared camera module, targets below 0°C appear as a first color (e.g., a white area) in the infrared image, while targets above 0°C appear as a second color (a darker area outside the white area). The formula for calculating the second ratio data is:

[0038] Where S' represents the area of ​​the pipe pixel pattern, S represents the area of ​​the third image pixel pattern, and r is the second scale data, which is expressed as a percentage for easier human observation.

[0039] like Figure 4 As shown, when the inflation is normal and there is no gas leakage, the white area is the infrared image of the inflation arm, and the dark area outside the white area is the infrared image of the surrounding area. The third image pixel pattern C is the combination of the white and dark areas. By calculating the ratio of the white area to the third image pixel area C, the proportion of the pipe pixel pattern when the inflation is normal and there is no gas leakage can be determined.

[0040] like Figure 5As shown, the step S300 of extracting a first region in the second image where the temperature is lower than the preset threshold value, and thresholding the second image to obtain the first proportion data further comprises steps S320 to S350.

[0041] In step S320, the first region is extracted and marked as a first pixel color.

[0042] In step S330, a second region in the second image where the temperature is higher than the preset threshold value is extracted and marked as a second pixel color. In an embodiment, the preset threshold value of the temperature is 0℃. The preset threshold value range can be adjusted in real time according to the natural gas temperature characteristics, such as being set to -10℃ to 0℃. The preset threshold value can also be automatically adjusted according to the actual field environment temperature to ensure accurate identification of the low-temperature leakage region.

[0043] In step S340, the second image is thresholded to obtain a first region pixel pattern including the first pixel color and a second region pixel pattern including the second pixel color, and the set of the first region pixel pattern and the second region pixel pattern is the second image pixel pattern. The first region pixel pattern includes the pipeline pixel pattern, and the second region pixel pattern includes the surrounding region pixel pattern. It can be understood that if gas leakage occurs, the first region pixel pattern includes the pipeline pixel pattern and the leaked gas pixel pattern (both temperatures are lower than 0℃).

[0044] In step S350, the area proportion of the first region pixel pattern relative to the second image pixel pattern is calculated to obtain the first proportion data. The calculation method of the first proportion data is the same as that of the second proportion data, which will not be repeated here.

[0045] It can be understood that when the pipeline is normally inflated and no gas leakage occurs, the infrared light image can capture the pipeline with a temperature lower than 0℃. Therefore, when setting the preset proportion data range, the proportion of the pipeline itself should be considered, and therefore the minimum value of the preset proportion data should be greater than the second proportion data to avoid detecting the normally inflated pipeline as gas leakage.

[0046] It can be understood that if gas leakage occurs, the area with a temperature lower than 0℃ in the infrared light image will expand. Therefore, if there is a difference between the first proportion data and the second proportion data, and the first proportion data is greater than the second proportion data, it can be judged that gas leakage occurs in the connection region of the inflated arm pipeline. The difference between the first proportion data and the second proportion data can be regarded as the area of gas leakage.

[0047] If gas leakage occurs, the temperature of the leaked gas will also be lower than 0℃, and it will also be displayed as white in the infrared light image. Compared with the case when the gas is normally filled, the area of the white region when the gas leaks will increase, and the first proportion data will also increase compared with the second proportion data. By setting a reasonable preset proportion data range, it can be known whether gas leakage occurs.

[0048] In order to further adapt to the field environment, it is necessary to limit the preset proportion data range. If the first proportion data is in the preset proportion data range, a leakage alarm prompt is issued, and if the first proportion data is not in the preset proportion data range, no leakage alarm prompt is issued. Because in the actual field environment, the area of gas leakage will only be within a certain range and basically will not reach an infinite size, on the other hand, some special cases are removed to prevent false positives. For example, in one embodiment, the preset proportion data range is 4.30%~12%. If the first proportion data suddenly increases and is greater than 12%, it is judged that it may be ice blocks, and the alarm prompt is suppressed.

[0049] The person skilled in the art can determine the specific preset proportion data range according to actual needs, such as pipeline area, field environment temperature, etc. The preset proportion data range is not limited in the present application.

[0050] The technical scheme of the present application uses infrared light images and calculates the first proportion data, which is beneficial to exclude the interference of ice blocks and normal low-temperature work of pipelines. The deep learning recognition of the visible light image can distinguish natural smoke from leakage smoke, which is beneficial to improve the accuracy of detection.

[0051] In the present embodiment, after the step S400 of judging that gas leakage occurs in the filling arm pipeline connection area, it further includes a step S500. In the step S500, the image is fused and saved. The first image and the second image after thresholding processing are fused and processed to obtain a fusion image containing visual morphological characteristics and temperature information of the leakage area, and the fusion image is transmitted and saved to a server, which is convenient for the operator to report and summarize regularly in the subsequent work, and is beneficial to improve the work efficiency.

[0052] In one embodiment, the stored fusion image contains temperature, time stamp, leakage level and other information, which is convenient for analyzing the leakage development process afterwards and provides a basis for fault troubleshooting.

[0053] For example, Figure 6As shown, the embodiment of the present application provides a device for detecting natural gas inflation arm gas leakage, which comprises an image acquisition module 100, a first image processing module 200, a second image processing module 300, and an alarm module 400. The image acquisition module 100 is used to acquire the image of the inflation arm pipeline connection area. The first image processing module 200 is used to identify the morphological features of the first image through a deep learning target detection algorithm. The second image processing module 300 is used to extract a first area in the second image where the temperature is lower than a preset threshold, and to perform thresholding processing on the second image, calculate the area ratio of the first area relative to the second image, obtain first ratio data, and compare the first ratio data with a preset ratio data range. The alarm module 400 is used to determine whether the first morphological detection result is a smoke-like area and whether the first ratio data is within the preset ratio data range, and to issue a leakage warning prompt.

[0054] It can be understood that the device for detecting natural gas inflation arm gas leakage can be a fixed device for the area around the pipeline, or a mobile device such as a portable detection equipment held by an operator or a patrol robot, and the image acquisition module 100, the first image processing module 200, the second image processing module 300, and the alarm module 400 are integrated in the mobile device.

[0055] Specifically, the image acquisition module 100 comprises a high-resolution visible light camera, an infrared light camera, and a synchronous trigger controller, and is electrically connected with the first image processing module 200 and the second image processing module 300. The visible light camera and the infrared light camera are coaxially installed on one side of the inflation arm connection, and the image time alignment is ensured through the hardware synchronization signal of the trigger controller to avoid image deviation.

[0056] In this embodiment, the alarm module 400 comprises a first prompt module and a second prompt module. The first prompt module is used to produce a voice broadcast prompt, and the second prompt module is used to issue a buzzer sound prompt and / or produce a warning light prompt. By configuring the first prompt module and the second prompt module, the voice broadcast prompt, the buzzer sound prompt, and / or the warning light prompt are combined, which is beneficial to timely remind the operator of gas leakage, facilitate the operator to timely repair and process, and is beneficial to improve safety.

[0057] Specifically, the alarm module 400 has a first alarm state and a second alarm state. If the first ratio data is within the ratio data range and the duration exceeds 3s, the first alarm state is entered, and the on-site voice broadcast prompt is started. If the first ratio data is within the ratio data range and the value is large, the second alarm state is switched, the buzzer sound prompt and / or the warning light prompt are issued, the server end is automatically controlled to close the inflation valve, and the leakage emergency work order is pushed to the operation and maintenance personnel.

[0058] The aboveFigures 1 to 6 The device for detecting gas leakage of natural gas inflatable arm in the embodiment of the present application is described in detail from the perspective of modular functional entities. The device for detecting gas leakage of natural gas inflatable arm in the embodiment of the present application is described in detail from the perspective of hardware processing.

[0059] Figure 7 Fig. 1 is a schematic diagram of a device for detecting gas leakage of natural gas inflatable arm provided by the embodiment of the present application. The device 500 for detecting gas leakage of natural gas inflatable arm can be different in configuration or performance, and can include one or more central processing units (CPU) 510 and a memory 520, and one or more storage media 530 (such as one or more mass storage devices) for storing application programs 533 or data 532. The memory 520 and the storage media 530 can be temporary storage or persistent storage. The programs stored in the storage media 530 can include one or more modules (not shown in the figure), each of which can include a series of instruction operations of the device 500 for detecting gas leakage of natural gas inflatable arm. Further, the processor 510 can be configured to communicate with the storage media 530 and execute the series of instruction operations in the storage media 530 on the device 500 for detecting gas leakage of natural gas inflatable arm.

[0060] The device 500 for detecting gas leakage of natural gas inflatable arm can also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input / output interfaces 560, and / or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art can understand that the device 500 for detecting gas leakage of natural gas inflatable arm can include more or fewer components than those shown, or some components can be combined, or different components can be arranged. Figure 7 The structure of the device for detecting gas leakage of natural gas inflatable arm shown does not constitute a limitation on the device for detecting gas leakage of natural gas inflatable arm, and can include more or fewer components than those shown, or some components can be combined, or different components can be arranged.

[0061] The present application also provides a device for detecting gas leakage of natural gas inflatable arm, which includes a memory and a processor. The memory stores computer readable instructions. When the computer readable instructions are executed by the processor, the processor executes the steps of the method for detecting gas leakage of natural gas inflatable arm in each of the above embodiments.

[0062] The application further provides a computer readable storage medium, which can be a nonvolatile computer readable storage medium or a volatile computer readable storage medium, and instructions are stored in the computer readable storage medium, and when the instructions are executed on a computer, the computer is caused to perform the steps of the method for detecting natural gas charging arm gas leakage.

[0063] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, and will not be described here.

[0064] The integrated unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the application or the whole or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the application. The foregoing storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0065] The above only describes the preferred embodiments of the application, and does not limit the patent scope of the application. Any equivalent structural transformation made according to the content of the specification and drawings, or direct / indirect application in other related technical fields is included in the patent protection scope of the application.

Claims

1. A method for detecting gas leakage in a natural gas filling arm, characterized in that, include: Images of the inflatable arm pipe connection area are acquired to obtain a first image and a second image that overlap at least partially. The first image is a visible light image of the inflatable arm pipe connection area, and the second image is an infrared light image of the inflatable arm pipe connection area. The morphological features of the first image are identified by a deep learning object detection algorithm to obtain the first morphological detection result; Extract a first region in the second image whose temperature is below a preset threshold, and perform thresholding processing on the second image. Calculate the area ratio of the first region relative to the second image to obtain first ratio data. Compare the first ratio data with a preset ratio data range, where the preset ratio data range is a preset range of the area ratio of the first region when there is a gas leak. If the first morphological detection result is determined to be smoke-like, and the first ratio data is within the preset ratio data range, then it is determined that a gas leak has occurred in the inflatable arm pipe connection area, and a leak alarm is issued.

2. The method for detecting gas leakage in a natural gas filling arm as described in claim 1, characterized in that, The step of identifying the first image morphological features using a deep learning object detection algorithm includes: Based on deep learning algorithms, visible light image samples containing smoke-like leakage features are trained to obtain a target detection model and preset smoke-like gas leakage features. The target detection model is used to identify and compare the morphological features of the first image to obtain the first morphological detection result. The first morphological detection result is compared with the preset smoke-like gas leakage characteristics to determine whether the first morphological detection result matches the preset smoke-like gas leakage characteristics. If the first morphological detection result matches the preset smoke-like gas leakage characteristics, it is determined that a gas leak has occurred in the inflatable arm pipe connection area.

3. The method for detecting gas leakage in a natural gas filling arm as described in claim 1, characterized in that, Before the step of thresholding the second image, the method further includes: obtaining proportional data when there is no gas leakage, including: A third image of the pipe and the surrounding area is obtained when the pipe is normally inflated and there is no gas leakage. The third image includes infrared light image information of the pipe and infrared light image information of the surrounding area. The temperature of the pipe is lower than the temperature of the surrounding area. Extract the infrared light image information of the pipeline and mark it as the first pixel color; extract the infrared light image information of the surrounding area and mark it as the second pixel color; The third image is thresholded to obtain a pipeline pixel pattern including the color of the first pixel and a surrounding area pixel pattern including the color of the second pixel. The set of the pipeline pixel pattern and the surrounding area pixel pattern is the pixel pattern of the third image. The area ratio of the pipe pixel pattern to the third image pixel pattern is calculated to obtain the second ratio data when there is no gas leakage.

4. The method for detecting gas leakage in a natural gas filling arm as described in claim 3, characterized in that, The step of extracting a first region in the second image whose temperature is below a preset threshold, performing thresholding processing on the second image, and calculating the area ratio of the first region relative to the second image to obtain first ratio data includes: Extract the first region and mark it with the first pixel color; Extract a second region in the second image whose temperature is higher than a preset threshold, and mark it as the second pixel color; The second image is thresholded to obtain a first region pixel pattern including the color of the first pixel and a second region pixel pattern including the color of the second pixel. The set of the first region pixel pattern and the second region pixel pattern is the second image pixel pattern. The first region pixel pattern includes a pipe pixel pattern and the second region pixel pattern includes a surrounding region pixel pattern. The area ratio of the pixel pattern in the first region to the pixel pattern in the second image is calculated to obtain the first ratio data.

5. The method for detecting gas leakage in a natural gas filling arm as described in claim 4, characterized in that, The minimum value of the preset ratio data range is greater than the second ratio data; If there is a difference between the first proportional data and the second proportional data, and the first proportional data is greater than the second proportional data, then it is determined that a gas leak has occurred in the connection area of ​​the inflatable arm pipe.

6. The method for detecting gas leakage in a natural gas filling arm as described in claim 1, characterized in that, After the step of determining that a gas leak has occurred in the connection area of ​​the inflatable arm pipe, the method further includes: The first image and the thresholded second image are fused together to obtain a fused image containing the visual morphological features and temperature information of the leak area, and the fused image is transmitted and saved to the server.

7. A device for detecting gas leakage in a natural gas filling arm, characterized in that, include: The image acquisition module is used to acquire images of the inflatable arm pipe connection area; The first image processing module is used to identify the morphological features of the first image through a deep learning object detection algorithm; The second image processing module is used to extract a first region in the second image whose temperature is lower than a preset threshold, perform thresholding processing on the second image, calculate the area ratio of the first region relative to the second image to obtain a first ratio data, and compare the first ratio data with a preset ratio data range. as well as The alarm module is used to determine whether the first morphological detection result is a smoke-like area and whether the first ratio data is within the preset ratio data range, and to issue a leak alarm prompt.

8. The apparatus for detecting gas leakage in a natural gas filling arm as described in claim 7, characterized in that, The alarm module includes a first prompt module and a second prompt module. The first prompt module is used to generate a voice broadcast prompt, and the second prompt module is used to emit a buzzer sound prompt and / or generate a warning light prompt.

9. A device for detecting gas leakage in a natural gas filling arm, characterized in that, The device includes: a memory and at least one processor, wherein the memory stores instructions; The at least one processor invokes the instructions in the memory to cause the device to perform the method for detecting gas leaks in a natural gas filling arm as described in any one of claims 1-6.

10. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the method for detecting gas leakage in a natural gas filling arm as described in any one of claims 1-6.

Images