Gas valve leakage detection method and system

Abstract

The present invention relates to a gas valve leakage detection method and system, including: obtaining video data of multiple streamers installed on the circumference of the valve to be detected; processing the video data and extracting key frames by frame sampling; performing image processing and recognition on the key frames to obtain the geometric center coordinates of each streamer in the key frames; calculating based on the geometric center coordinates of each streamer to obtain the Euclidean distance between the current key frame of each streamer and the previous preset key frames; judging whether the valve to be detected is leaking according to the Euclidean distance between the current key frame of each streamer and the previous preset key frames. The present invention uses the movement amplitude of the streamer to intuitively reflect the operating status of the valve, converts the non-visual features of the valve leakage into visual features, can effectively filter the vibration interference in the environment, thereby realizing accurate judgment of whether the valve is leaking, and meeting the diverse needs in the industrial environment.

Description

Technical Field

[0001] The present invention relates to the technical field of valve leakage detection, and more specifically, to a gas valve leakage detection method and system. Background Art

[0002] Valves are key gas or fluid control components in industrial systems, and their operating status directly affects the safety and stability of the system. Valve leakage may not only lead to waste of resources, but also cause serious safety hazards. At present, traditional valve leakage detection methods mainly rely on acoustic wave detection, ultrasonic monitoring or pressure change analysis. However, these methods have some limitations. For example, acoustic wave detection is easily affected by environmental influences, ultrasonic monitoring equipment is complex and costly, and pressure change analysis requires invasive modification of the pipeline system and is difficult to monitor in real time. Therefore, existing technologies are difficult to meet the diverse needs in industrial environments. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a gas valve leakage detection method and system in view of the problems existing in the prior art.

[0004] The technical solution adopted by the present invention to solve the technical problem is: constructing a gas valve leakage detection method, comprising the following steps: Acquire video data of a plurality of streamers installed on the circumference of the valve to be inspected; Processing the video data to extract key frames by frame sampling; Performing image processing and recognition on the key frame to obtain the geometric center coordinates of each streamer in the key frame; Calculating based on the geometric center coordinates of each streamer, obtaining the Euclidean distance between the current key frame of each streamer and the previous preset key frames; Whether the valve to be detected is leaking is determined according to the Euclidean distance between the current key frame of each streamer and the previously preset key frames.

[0005] In the gas valve leakage detection method of the present invention, the processing of the video data and extracting key frames by frame sampling includes: The video data is subjected to frame sampling processing at a preset time interval to obtain the key frame.

[0006] In the gas valve leakage detection method of the present invention, the calculation based on the geometric center coordinates of each streamer to obtain the Euclidean distance between the current key frame of each streamer and the previous preset key frames includes: Determine the sliding window; Based on the current key frame of each streamer and the sliding window, the Euclidean distance between the geometric center coordinates of each streamer at the current key frame and the geometric center coordinates of the previous preset key frames is calculated; the number of the previous preset key frames is determined by the sliding window.

[0007] In the gas valve leakage detection method of the present invention, the Euclidean distance is calculated by the following formula: ; Where d is the Euclidean distance, ( , )and( , ) are the geometric center coordinates of the same ribbon at two key frames.

[0008] In the gas valve leakage detection method of the present invention, judging whether the valve to be detected is leaking according to the Euclidean distance between the current key frame of each streamer and the previously preset key frames includes: Determine whether the Euclidean distance between the current key frame of each streamer and the previous preset key frames satisfies that the distance of a single streamer is increasing, and the number of streamers with an increasing trend among all streamers meets the set threshold; If yes, it is determined that the valve to be detected is leaking; If not, it is determined that the valve to be tested has no leakage.

[0009] The gas valve leakage detection method of the present invention further includes: If it is determined that the valve to be detected is leaking, a leakage alarm signal is output.

[0010] The present invention also provides a gas valve leakage detection system, which is applied to the gas valve leakage detection method described above, comprising: a plurality of streamers arranged along the circumference of the valve to be detected, an image acquisition device installed on site, and a central processing system communicating with the image acquisition device; The image acquisition device is used to acquire images of the plurality of streamers, obtain video data of the plurality of streamers, and send the video data of the plurality of streamers to the central processing system; The central processing system is used to: Processing the video data to extract key frames by frame sampling; Performing image processing and recognition on the key frame to obtain the geometric center coordinates of each streamer in the key frame; Calculating based on the geometric center coordinates of each streamer, obtaining the Euclidean distance between the current key frame of each streamer and the previous preset key frames; Whether the valve to be detected is leaking is determined according to the Euclidean distance between the current key frame of each streamer and the previously preset key frames, and a leakage alarm signal is output when it is determined that the valve to be detected is leaking.

[0011] In the gas valve leakage detection system described in the present invention, the width of the ribbon is less than one twelfth of the circumference of the valve to be detected, and the length is greater than three times the width; the number of the multiple ribbons is greater than or equal to twelve, and the multiple ribbons are installed at equal intervals on the circumference of the valve to be detected.

[0012] In the gas valve leakage detection system described in the present invention, the image acquisition device includes multiple cameras; the multiple cameras are all installed on site, and the installation height of the multiple cameras is greater than the height of the ribbon installation plane, and the shooting angles of the multiple cameras are: deflection angles of 15 degrees to 45 degrees.

[0013] The gas valve leakage detection system of the present invention further includes: a remote terminal; The remote terminal communicates with the central processing system and is used for receiving the leakage alarm signal and outputting it for display.

[0014] The implementation of the gas valve leakage detection method and system of the present invention has the following beneficial effects: including: obtaining video data of multiple streamers installed on the circumference of the valve to be detected; processing the video data and extracting key frames by frame sampling; performing image processing and recognition in the key frames to obtain the geometric center coordinates of each streamer in the key frames; calculating based on the geometric center coordinates of each streamer to obtain the Euclidean distance between the current key frame of each streamer and the previous preset key frames; judging whether the valve to be detected is leaking according to the Euclidean distance between the current key frame of each streamer and the previous preset key frames. The present invention uses the movement amplitude of the streamer to intuitively reflect the operating status of the valve, converts the non-visual features of the valve leakage into visual features, can effectively filter the vibration interference in the environment, thereby realizing accurate judgment of whether the valve is leaking, and meeting the diverse needs in the industrial environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which: Figure 1 It is a flow chart of the gas valve leakage detection method provided by the present invention; Figure 2 It is a principle block diagram of the gas valve leakage detection system provided by the present invention; Figure 3 It is a schematic diagram of the installation of the streamer provided by the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] In order to solve the problems existing in the existing gas valve leakage detection, the present invention provides a non-contact, efficient and real-time solution for valve leakage monitoring based on computer video technology of target detection. The present invention installs a ribbon 101 on the valve, uses the movement amplitude of the ribbon 101 to intuitively reflect the operating state of the valve, converts the non-visual characteristics of valve leakage into visual characteristics, and then uses computer video algorithms to detect and analyze the movement characteristics of the ribbon 101, which can effectively filter out vibration interference in the environment, thereby accurately judging whether the valve is leaking.

[0018] refer to Figure 1 , Figure 1 A flow chart of a preferred embodiment of a gas valve leakage detection method provided by the present invention.

[0019] Specifically, Figure 1 As shown, the gas valve leakage detection method comprises the following steps: Step S101: Acquire video data of a plurality of streamers 101 installed around the circumference of a valve to be inspected.

[0020] In the embodiment of the present invention, the image of the streamer 101 can be captured by the image capture device 100 installed on site to obtain video data including each streamer 101 , and the video data can be sent to the central processing system 200 .

[0021] Step S102: Process the video data and extract key frames by frame sampling.

[0022] Optionally, in an embodiment of the present invention, processing the video data to extract key frames by frame sampling includes: performing frame sampling processing on the video data at preset time intervals to obtain key frames.

[0023] Specifically, the image acquisition device 100 transmits the data streams of all the streamers 101 on site to the central processing system 200 in real time, and the central processing system 200 extracts the key frames of the video data from the continuous frames of the input video data stream at a preset time interval (for example, one frame is selected from five frames as a key frame). Thus, a key frame set can be obtained.

[0024] Optionally, in an embodiment of the present invention, the preset time interval is adjustable, and can be adjusted according to the vibration conditions at the site (such as vibration patterns or cycles).

[0025] Step S103: performing image processing and recognition in the key frame to obtain the geometric center coordinates of each streamer 101 in the key frame.

[0026] Specifically, after the key frames are identified in step S102, if the key frame set is represented as S={ , , ...}, the central processing system 200 will perform image processing and recognition in each key frame to obtain the geometric center coordinates of the key frame of each streamer 101. For example, a semantic understanding and segmentation algorithm based on a convolutional neural network can be run to classify each pixel in each key frame image to identify the position and geometric center coordinates of each streamer 101. Of course, the present invention can also use other image recognition algorithms to realize the recognition of the geometric position of each key frame image of each streamer 101, such as edge detection or optical flow method, as long as the algorithm can recognize the geometric center coordinates of an object from an image.

[0027] Step S104: Calculate based on the geometric center coordinates of each streamer 101 to obtain the Euclidean distance between the current key frame and the previous preset key frames of each streamer 101 .

[0028] Optionally, in the embodiment of the present invention, the calculation based on the geometric center coordinates of each streamer 101 to obtain the Euclidean distance between the current key frame of each streamer 101 and the previous preset key frames includes: determining a sliding window; and calculating the Euclidean distance between the geometric center coordinates of each streamer 101 at the current key frame and the geometric center coordinates of the previous preset key frames based on the current key frame of each streamer 101 and the sliding window. The number of the previous preset key frames is determined by the sliding window.

[0029] Optionally, in the embodiment of the present invention, the Euclidean distance is calculated by the following formula: ; Where d is the Euclidean distance, ( , )and( , ) are the geometric center coordinates of the same ribbon at two key frames.

[0030] Step S105: determining whether the valve to be detected is leaking according to the Euclidean distance between the current key frame of each streamer 101 and the previously preset key frames.

[0031] Optionally, in an embodiment of the present invention, determining whether the valve to be detected is leaking based on the Euclidean distance between the current key frame of each streamer 101 and the previously preset key frames includes: determining whether the Euclidean distance between the current key frame of each streamer 101 and the previously preset key frames satisfies that the distance of a single streamer 101 is increasing, and the number of streamers 101 that are increasing in all streamers 101 satisfies a set threshold; if so, it is determined that the valve to be detected is leaking; if not, it is determined that the valve to be detected is not leaking. Among them, the size of the sliding window can be set according to conditions such as the on-site valve air pressure, the size and quality of the streamer 101, and the on-site vibration. The threshold setting of the streamer 101 is set according to the valve type, application scenario, and on-site environment. For example, it can be set to 80%, 70%, etc.

[0032] Furthermore, the gas valve leakage detection method further includes: if it is determined that the valve to be detected is leaking, outputting a leakage alarm signal.

[0033] For example, let the sliding window size be w, and set the threshold to X%. Then for the latest key frame (i.e. the current key frame) The central processing system 200 will calculate the number of streamers 101 at The geometric center coordinates at The Euclidean distance of the geometric center coordinates when (denoted as the single streamer 101 ), each streamer 101 in The geometric center coordinates at The Euclidean distance of the geometric center coordinates when (denoted as the single streamer 101 ), until each streamer 101 The geometric center coordinates at The Euclidean distance of the geometric center coordinates when (denoted as the single streamer 101 ). If the distance of a single streamer 101 is increasing (i.e. < <...< < ), it is determined that the streamer 101 is blown up, and if the number of streamers 101 with increasing distances exceeds X% of the total number of streamers 101, it is determined that the valve is leaking. At this time, the central processing system 200 outputs a leakage alarm signal, wherein the leakage alarm signal will be sent to the administrator or on-site operator.

[0034] For example, if the sliding window size w=5 and X=80, then for the latest key frame The central processing system 200 will calculate the number of streamers 101 at The centroid (geometric center) of the ribbon 101 at { , , , }, denoted as D i ={ , , , }. If more than 80% of the streamer 101 D i satisfy < < < , the valve is judged to be leaking and an alarm is sent to the administrator and on-site operator.

[0035] The gas valve leakage detection method of the present invention is a gas valve leakage detection method based on a computer vision target detection algorithm. In this method, first, the video data collected by the front-end camera flows back to the computer system in the form of continuous frames. Through frame sampling, one key frame is extracted from every 5 frames of the continuous frames and put into the algorithm analysis to filter out the image noise caused by the jitter of the device and improve the algorithm response speed. Then, the semantic understanding and segmentation algorithm based on the convolutional neural network deployed in the computer system after pre-training is completed to identify the position and geometric center coordinates of each streamer 101 by classifying each pixel in each frame of the image. After completing the position identification of each streamer 101 in each key frame, the computer system will calculate the distance between each streamer 101 and its position in the previous W key frames. If the distance change trend of a streamer 101 in W consecutive key frames is rising, the computer system determines that the streamer 101 is blown up. If a certain proportion of the streamers 101 are blown up in a certain frame, the system will output an alarm, that is, the number of moving streamers 101 is combined for determination. By combining the number of moving streamers 101 for determination, the system recognition accuracy can be improved. This technology has the characteristics of simple deployment, high monitoring efficiency and strong reliability, providing an efficient valve operation status monitoring solution.

[0036] refer to Figure 3 The present invention also provides a gas valve leakage detection system, which can be applied to the gas valve leakage detection method disclosed in the embodiment of the present invention.

[0037] Specifically, Figure 3 As shown, the gas valve leakage detection system includes: a plurality of streamers 101 arranged along the circumference of the valve to be detected, an image acquisition device 100 installed on site, and a central processing system 200 communicating with the image acquisition device 100 .

[0038] In the embodiment of the present invention, the width of the ribbon 101 is less than one-twelfth of the circumference of the valve to be detected, and the length is greater than three times the width; the number of the plurality of ribbons 101 is greater than or equal to twelve, and the plurality of ribbons 101 are installed at equal intervals around the circumference of the valve to be detected. The ribbon 101 can be in a color that is more prominent than the surrounding environment, for example, a color such as (RGB value #ff0000) can be selected. The ribbon 101 is installed at equal intervals around the valve on a plane by pasting or the like, as shown in the following example. Figure 3 As shown. Among them, Figure 3 This is a top view of the streamer 101 installed on the pipeline valve. The actual number of installed streamers 101 is not limited.

[0039] In the embodiment of the present invention, the image acquisition device 100 is used to acquire images of the plurality of streamers 101, obtain video data of the plurality of streamers 101, and send the video data of the plurality of streamers 101 to the central processing system 200. Optionally, the image acquisition device 100 includes a plurality of cameras; the plurality of cameras are all installed on site, and the installation height of the plurality of cameras is greater than the height of the installation plane of the streamers 101, and the shooting angles of the plurality of cameras are: a deflection angle of 15 degrees to 45 degrees.

[0040] Specifically, at least two cameras need to be installed, and the installation distance between the two cameras needs to be far enough to ensure that all the streamers 101 on each side of the valve can be included in the picture. The camera resolution is required to be greater than or equal to 1080p; the frame rate is required to be greater than or equal to 30Hz; it is recommended that the installation height is greater than the height of the installation plane of the streamer 101, and the camera should be filmed at a depression angle of 15 to 45 degrees; the camera needs to be firmly fixed on a solid building structure such as a wall or steel beam.

[0041] The present invention converts the non-visual features of gas valve leakage into visual features by installing a ribbon 101 with a prominent color around the valve and a camera installed on site, and transmits the on-site data stream to the central processing system 200 (i.e., the computer system) in real time.

[0042] In the embodiment of the present invention, the central processing system 200 is used to: process the video data of multiple streamers 101 to determine the key frame of each streamer 101; perform image processing and recognition based on the key frame of each streamer 101 to obtain the geometric center coordinates of each streamer 101; perform calculations based on the geometric center coordinates of each streamer 101 to obtain the Euclidean distance between the current key frame of each streamer 101 and the previously preset key frames; determine whether the valve to be detected is leaking based on the Euclidean distance between the current key frame of each streamer 101 and the previously preset key frames, and output a leakage alarm signal when it is determined that the valve to be detected is leaking.

[0043] Furthermore, if Figure 2As shown, the gas valve leakage detection system also includes: a remote terminal 300; the remote terminal 300 communicates with the central processing system 200, and is used to receive the leakage alarm signal and output it for display. Optionally, the remote terminal 300 can be a management terminal (computer) used by an administrator, or a handheld terminal used by a field operator, etc.

[0044] Specifically, the specific coordination operation process between the units in the gas valve leakage detection system here can refer to the above-mentioned gas valve leakage detection method, which will not be repeated here.

[0045] It should be noted that the present invention is not only applicable to leakage detection of gas valves, but also applicable to leakage detection of pipelines (with gas in the pipeline).

[0046] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0047] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0048] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0049] The above embodiments are only for illustrating the technical concept and features of the present invention, and their purpose is to enable people familiar with the technology to understand the content of the present invention and implement it accordingly, and they cannot limit the scope of protection of the present invention. All equivalent changes and modifications made to the scope of the claims of the present invention should fall within the scope of the claims of the present invention.

Claims

1. A gas valve leakage detection method, characterized in that: The following steps are involved: Acquire video data of a plurality of streamers installed on the circumference of the valve to be inspected; Processing the video data to extract key frames by frame sampling; Performing image processing and recognition on the key frame to obtain the geometric center coordinates of each streamer in the key frame; Calculating based on the geometric center coordinates of each streamer, obtaining the Euclidean distance between the current key frame of each streamer and the previous preset key frames; Whether the valve to be detected is leaking is determined according to the Euclidean distance between the current key frame of each streamer and the previously preset key frames.

2. The gas valve leakage detection method according to claim 1, characterized in that: The processing of the video data to extract key frames by frame sampling includes: The video data is subjected to frame sampling processing at a preset time interval to obtain the key frame.

3. The gas valve leakage detection method according to claim 1, characterized in that: The calculating based on the geometric center coordinates of each streamer to obtain the Euclidean distance between the current key frame of each streamer and the previous preset key frames includes: Determine the sliding window; Based on the current key frame of each streamer and the sliding window, the Euclidean distance between the geometric center coordinates of each streamer at the current key frame and the geometric center coordinates of the previous preset key frames is calculated; the number of the previous preset key frames is determined by the sliding window.

4. The gas valve leakage detection method according to claim 3, characterized in that: The Euclidean distance is calculated by the following formula: ； Where d is the Euclidean distance, ( , )and( , ) are the geometric center coordinates of the same ribbon at two key frames.

5. The gas valve leakage detection method according to claim 1, characterized in that: The step of determining whether the valve to be detected is leaking according to the Euclidean distance between the current key frame of each streamer and the previously preset key frames includes: Determine whether the Euclidean distance between the current key frame of each streamer and the previous preset key frames satisfies that the distance of a single streamer is increasing, and the number of streamers with an increasing trend among all streamers meets the set threshold; If yes, it is determined that the valve to be detected is leaking; If not, it is determined that the valve to be tested has no leakage.

6. The gas valve leakage detection method according to any one of claims 1 to 5, characterized in that: Also includes: If it is determined that the valve to be detected is leaking, a leakage alarm signal is output.

7. A gas valve leakage detection system, applied to the gas valve leakage detection method according to any one of claims 1 to 6, characterized in that: include: A plurality of streamers arranged along the circumference of the valve to be inspected, an image acquisition device installed on site, and a central processing system communicating with the image acquisition device; The image acquisition device is used to acquire images of the plurality of streamers, obtain video data of the plurality of streamers, and send the video data of the plurality of streamers to the central processing system; The central processing system is used to: Processing the video data to extract key frames by frame sampling; Performing image processing and recognition on the key frame to obtain the geometric center coordinates of each streamer in the key frame; Calculating based on the geometric center coordinates of each streamer, obtaining the Euclidean distance between the current key frame of each streamer and the previous preset key frames; Whether the valve to be detected is leaking is determined according to the Euclidean distance between the current key frame of each streamer and the previously preset key frames, and a leakage alarm signal is output when it is determined that the valve to be detected is leaking.

8. The gas valve leakage detection system according to claim 7, characterized in that: The width of the ribbon is less than one twelfth of the circumference of the valve to be detected, and the length is greater than three times the width; the number of the multiple ribbons is greater than or equal to twelve, and the multiple ribbons are installed at equal intervals on the circumference of the valve to be detected.

9. The gas valve leakage detection system according to claim 7, characterized in that: The image acquisition device includes a plurality of cameras; the plurality of cameras are all installed on site, and the installation height of the plurality of cameras is greater than the height of the ribbon installation plane, and the shooting angles of the plurality of cameras are: an angle of 15 degrees to 45 degrees.

10. The gas valve leakage detection system according to claim 7, characterized in that: Also includes: a remote terminal; The remote terminal communicates with the central processing system and is used for receiving the leakage alarm signal and outputting it for display.

Images