Method and device for detecting copper pipe welding, electronic equipment and storage medium

Abstract

The application relates to a copper pipe welding detection method and device, electronic equipment and a storage medium. The method comprises the following steps: continuously acquiring a first monitoring image; wherein the first monitoring image is a copper pipe image in a heating process before solder is added; the copper pipe temperature in the heating process is detected in real time according to the first monitoring image, and a copper pipe temperature detection result is determined; a second monitoring image is continuously acquired; wherein the second monitoring image is a welding flame image in a welding process after the solder is added; welding defects in the welding process are detected in real time according to the second monitoring image, and a welding defect detection result is determined; wherein the welding defects at least include a pinhole defect and a pore defect. Through the technical scheme provided in the application, a detection result is generated in real time, the whole process of copper pipe welding is monitored, and the copper pipe welding quality is detected in the process of copper pipe welding.

Description

Technical Field

[0001] This application relates to the field of image detection, and more particularly to a method, apparatus, electronic device, and storage medium for detecting copper pipe welding. Background Technology

[0002] Copper pipe welding can improve the connection strength, sealing, corrosion resistance, and aesthetics of air conditioning copper pipes and joints, and is one of the key factors determining the performance and lifespan of air conditioners. Copper pipe welding requires a certain level of skill from the welder and adherence to specific temperature requirements. Improper welding can lead to defects such as weak welds, pinholes, and porosity.

[0003] Existing technologies include methods for inspecting the welding quality of copper pipes, but these methods primarily target defects after welding. However, inspecting the welding quality after completion, even if defects are detected and improvements are made, wastes time and manpower. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and storage medium for detecting copper pipe welding, so as to detect the quality of copper pipe welding during the copper pipe welding process.

[0005] In a first aspect, this application provides a method for detecting copper pipe welding, the method comprising:

[0006] Continuously acquire the first monitoring image; wherein, the first monitoring image is an image of the copper tube during the heating process before the addition of solder;

[0007] The temperature of the copper tube during the heating process is detected in real time based on the first monitoring image, and the detection result of the copper tube temperature is determined.

[0008] Continuously acquire a second monitoring image; wherein the second monitoring image is a welding flame image during the welding process after the addition of solder;

[0009] The welding defects in the welding process are detected in real time based on the second monitoring image to determine the welding defect detection results; wherein the welding defects include at least sand hole defects and porosity defects.

[0010] In one feasible embodiment of this application, the copper tube temperature detection result is either a normal temperature result or a temperature abnormal result. The copper tube temperature during the heating process is detected in real time based on the first monitoring image to determine the copper tube temperature detection result, including:

[0011] Based on the first monitoring image, determine whether the copper tube color tone is the standard color tone during the heating process;

[0012] If the copper tube color tone is the standard color tone, the copper tube temperature detection result is determined to be the normal temperature result;

[0013] If the copper tube color tone is not the standard color tone, the copper tube temperature detection result is determined to be the temperature anomaly result.

[0014] In one feasible embodiment of this application, determining whether the copper tube hue is a standard hue during the heating process based on the first monitoring image includes:

[0015] The first monitoring image is converted from RGB color space to HSV color space to determine the HSV histogram of the first monitoring image, and the hue curve is determined in the HSV histogram; wherein, the vertical axis of the HSV histogram represents the frequency of hue occurrence, and the horizontal axis of the HSV histogram represents the hue.

[0016] The maximum hue frequency is determined based on the hue curve. The hue corresponding to the maximum hue frequency is determined in the HSV histogram. It is then determined whether the hue corresponding to the maximum hue frequency is within the range of the hue corresponding to the standard hue.

[0017] If the hue corresponding to the maximum hue frequency is within the hue range corresponding to the standard hue, it is determined that the hue of the copper tube during the heating process is the standard hue;

[0018] If the hue corresponding to the maximum hue frequency is not within the range of the hue corresponding to the standard hue, it is determined that the hue of the copper tube is not the standard hue during the heating process.

[0019] In one feasible embodiment of this application, the welding defect detection result includes the trachoma defect detection result, which is either a trachoma detection result or a trachoma-free result. The welding defects in the welding process are detected in real time based on the second monitoring image to determine the welding defect detection result, including:

[0020] Based on the second monitoring image, determine whether the welding flame simultaneously produces white smoke and white light;

[0021] When the welding flame simultaneously produces white smoke and white light, the trachoma defect detection result is determined to be the presence of trachoma.

[0022] If the welding flame does not simultaneously produce white smoke and white light, the result of the trachoma defect detection is determined to be the result of no trachoma.

[0023] In one feasible embodiment of this application, determining whether the welding flame simultaneously produces white smoke and white light based on the second monitoring image includes:

[0024] Convert the second monitoring image into a grayscale image;

[0025] The grayscale image is segmented by a segmentation threshold to identify white pixel blocks in the grayscale image; wherein the segmentation threshold is determined based on the pixel value of the pixel in the grayscale image.

[0026] If the white pixel block is detected, the type of the white pixel block is determined based on its brightness; wherein the type of the white pixel block is either a white smoke pixel block or a white light pixel block.

[0027] If both the white smoke pixel block and the white light pixel block are detected simultaneously, it is determined that the welding flame produces both white smoke and white light.

[0028] If the white smoke pixel block and the white light pixel block are not detected simultaneously, it is determined that the welding flame does not produce white smoke and white light at the same time.

[0029] In one feasible embodiment of this application, the welding defect detection result includes a porosity defect detection result, which is either a porosity result or a porosity-free result. The welding defects in the welding process are detected in real time based on the second monitoring image to determine the welding defect detection result, including:

[0030] Determine whether the welding flame is a reducing flame based on the second monitoring image;

[0031] When the welding flame is the reducing flame, the porosity defect detection result is determined to be the porosity result;

[0032] If the welding flame is not the reducing flame, the porosity defect detection result is determined to be the no-porosity result.

[0033] In one feasible embodiment of this application, determining whether the welding flame is a reducing flame based on the second monitoring image includes:

[0034] The perimeter of the welding flame edge, the flame hue, and the flame texture are determined based on the second monitoring image; wherein, the perimeter of the flame edge is determined by edge detection, the flame hue is determined by the HSV histogram of the second monitoring image, and the flame texture is determined by the gray-level co-occurrence matrix;

[0035] If the perimeter of the flame edge is greater than the perimeter threshold, the flame hue is not blue, and the flame texture is a cloudy flame, then the welding flame is determined to be a reducing flame.

[0036] If the perimeter of the flame edge is less than or equal to the perimeter threshold, the flame hue is blue, or the flame texture is transparent, then the welding flame is determined not to be a reducing flame.

[0037] Secondly, this application provides a detection device for copper pipe welding, the device comprising:

[0038] The first acquisition module is used to continuously acquire a first monitoring image; wherein, the first monitoring image is an image of the copper tube during the heating process before the addition of solder;

[0039] The first detection module is used to detect the temperature of the copper tube during the heating process in real time based on the first monitoring image, and determine the copper tube temperature detection result.

[0040] The second acquisition module is used to continuously acquire the second monitoring image; wherein the second monitoring image is a welding flame image during the welding process after the addition of solder;

[0041] The second detection module is used to perform real-time detection of welding defects in the welding process based on the second monitoring image, and determine the welding defect detection result; wherein the welding defects include at least sand hole defects and porosity defects.

[0042] Thirdly, this application provides an electronic device, comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus, wherein the processor is configured to execute a copper pipe welding detection method as described in the first aspect of this application.

[0043] Fourthly, this application also provides a computer storage medium storing computer-executable instructions for executing the copper pipe welding detection method described in the first aspect of this application.

[0044] The technical solutions provided in this application have the following advantages compared with the prior art:

[0045] The technical solution provided in this application embodiment continuously acquires a first monitoring image; wherein the first monitoring image is an image of a copper tube during the heating process before the addition of solder; the temperature of the copper tube during the heating process is detected in real time based on the first monitoring image to determine the copper tube temperature detection result; continuously acquires a second monitoring image; wherein the second monitoring image is an image of a welding flame during the welding process after the addition of solder; welding defects during the welding process are detected in real time based on the second monitoring image to determine the welding defect detection result; wherein the welding defects include at least sand hole defects and porosity defects.

[0046] As can be seen, in the technical solution provided in this application, the temperature of the copper tube is detected in real time through copper tube images during the heating process, and the welding flame is detected in real time through flame images during the welding process. Corresponding detection results are generated in real time, realizing the monitoring of the entire process of copper tube welding, so as to realize the detection of copper tube welding quality during the copper tube welding process. Attached Figure Description

[0047] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0049] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0050] Figure 1 This is a schematic diagram of the setup of a copper pipe welding detection system that can implement the copper pipe welding detection method provided in the embodiments of this application;

[0051] Figure 2 A schematic flowchart illustrating a method for detecting copper pipe welding provided in an embodiment of this application;

[0052] Figure 3 A diagram showing the change in welding flame during welding defect detection in a copper tube welding inspection method provided in this application embodiment;

[0053] Figure 4 A schematic diagram of the overall process of a copper pipe welding inspection method provided in an embodiment of this application;

[0054] Figure 5 A schematic diagram of the structure of a copper pipe welding detection device provided in an embodiment of this application;

[0055] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0057] The following disclosure provides numerous different embodiments or examples for implementing various structures of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of the invention. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0058] To address the problem that existing technologies can only inspect welding quality after welding is completed, this application provides a method, apparatus, electronic device, and storage medium for inspecting copper pipe welding, which can detect the welding quality of copper pipes during the welding process.

[0059] In the technical solution provided in this application, a corresponding copper pipe welding detection system can be set up in the copper pipe welding work area. This system can implement the copper pipe welding detection method provided in this application. Figure 1 This is a schematic diagram of the setup of a copper pipe welding detection system that can implement the copper pipe welding detection method provided in the embodiments of this application. (Refer to...) Figure 1 The system may include a camera device, a welding device, and a computer processing device.

[0060] A camera device is installed in the copper pipe welding work area and connected to a computer processing unit. The camera device is used to capture video or images of the copper pipe welding process and transmit the captured video or images to the computer processing unit.

[0061] The video or images captured by the camera device need to include the welding flame and the welding area of ​​the copper pipe, such as... Figure 1 As shown, the camera device does not need to be directly facing the welding flame; it is best to maintain a certain angle with the welding flame. Setting the camera device at a certain angle to the welding flame facilitates observation of changes in the welding flame's state.

[0062] The computer processing unit is used to receive video or images captured by the camera device and execute the copper pipe welding detection method provided in this application. Simultaneously, a user interaction device can be configured to communicate with the computer processing unit. Welders can wear the user interaction device to obtain relevant information from the computer processing unit, thereby better understanding the welding process of the copper pipe and the welding flame.

[0063] Figure 2 A flowchart illustrating a method for detecting copper pipe welding provided in this application embodiment is shown below. Figure 2 The copper pipe welding detection method provided in this application specifically includes the following steps:

[0064] S1: Continuously acquire the first monitoring image; wherein, the first monitoring image is an image of the copper tube during the heating process before the addition of solder;

[0065] Specifically, the first detection image is an image of the copper tube during the heating process before the addition of solder. In one feasible embodiment of this application, the first monitoring image is obtained from the video of the entire copper tube welding process captured by a camera device.

[0066] Specifically, when the welder begins welding, the camera is activated and begins recording the entire process of welding the copper pipe. The camera then transmits the video of the entire welding process to a computer processing unit in real time. The computer processing unit uses image region segmentation to separate the area where the copper pipe is being welded from the area of ​​the welding flame within the video. The image set obtained from the area where the copper pipe is being welded is used as the first monitoring image.

[0067] In one feasible embodiment of this application, image region segmentation of the entire copper pipe welding process video can be performed using image region segmentation software, specifically OpenCV. By setting the ROI (Region of Interest) in OpenCV, image region segmentation of the entire copper pipe welding process video can be achieved.

[0068] S2: Real-time detection of copper tube temperature during the heating process based on the first monitoring image, and determination of copper tube temperature detection result;

[0069] Specifically, copper pipe welding operations can generally be divided into a heating process and a welding process, with the addition of solder as the time point. During the heating process, the temperature of the copper pipe is raised to a certain value by the welding flame. During the welding process, the solder is heated by the welding flame to weld the copper pipe.

[0070] During the heating process, the temperature of the copper tube can be monitored in real time based on the first monitoring image, ensuring that the copper tube temperature remains within a reasonable range. In one feasible embodiment of this application, the temperature of the copper tube can be determined by detecting the color tone of the welded copper tube. Specifically, the copper tube temperature detection result is either a normal temperature result or an abnormal temperature result. The copper tube temperature is monitored in real time during the heating process based on the first monitoring image to determine the copper tube temperature detection result, which can be achieved through the following steps:

[0071] Determine whether the copper tube color is the standard color during the heating process based on the first monitoring image;

[0072] If the copper pipe color tone is the standard color tone, the copper pipe temperature test result is determined to be a normal temperature result;

[0073] If the copper pipe's color tone is not the standard color tone, the copper pipe temperature detection result is determined to be an abnormal temperature result.

[0074] Specifically, the standard color tone differs depending on the material of the copper pipe. For example, the copper pipes commonly used for welding in refrigeration systems are phosphorus deoxidized copper. It is more suitable to add solder when phosphorus deoxidized copper is heated to red, so the standard color tone of welded copper pipes made of phosphorus deoxidized copper is red.

[0075] When the welded copper pipe is heated to a certain temperature, its color changes. When the color of the welded copper pipe changes to the standard color, it indicates that the current temperature of the copper pipe is appropriate, and the temperature detection result is determined to be normal. When the color of the welded copper pipe does not change to the standard color, it indicates that the current temperature of the copper pipe is too high or too low, and the temperature detection result is determined to be abnormal.

[0076] In one feasible embodiment of this application, in order to accurately determine whether the copper tube color tone is a standard color tone during the heating process, the determination can be made based on the HSV histogram of the first monitoring image. In this embodiment, determining whether the copper tube color tone is a standard color tone during the heating process can be achieved through the following steps:

[0077] The first monitoring image is converted from RGB color space to HSV color space to determine the HSV histogram of the first monitoring image, and the hue curve is determined in the HSV histogram; where the vertical axis of the HSV histogram represents the frequency of hue occurrence, and the horizontal axis of the HSV histogram represents the hue.

[0078] Determine the frequency of the maximum hue based on the hue curve, identify the hue corresponding to the frequency of the maximum hue in the HSV histogram, and determine whether the hue corresponding to the frequency of the maximum hue is within the range of the hue corresponding to the standard hue.

[0079] If the hue corresponding to the maximum hue frequency is within the hue range corresponding to the standard hue, then the hue of the copper tube during the heating process is determined to be the standard hue.

[0080] If the hue corresponding to the maximum hue frequency is not within the range of the hue corresponding to the standard hue, it is determined that the hue of the copper tube is not the standard hue during the heating process.

[0081] Specifically, the parameters in the HSV histogram are hue (H), saturation (S), and value (V). The hue histogram in the HSV histogram uses the vertical axis to represent the frequency of hue occurrence and the horizontal axis to represent hue. Therefore, the hue curve actually describes the frequency of different hues in the first monitoring image.

[0082] Find the frequency of the maximum hue in the hue curve to determine the main hue in the first monitoring image. Compare the hue corresponding to the frequency of the maximum hue with the hue corresponding to the standard hue to determine whether the copper tube hue is a standard hue.

[0083] In one feasible embodiment of this application, there can be multiple standard hues, but these standard hues are relatively similar colors. For example, orange-red, orange-yellow, and yellow-red are actually all red hues. Therefore, each standard hue corresponds to a hue range. By determining whether the hue corresponding to the highest frequency of occurrence is within the hue range corresponding to the standard hue, it can be determined whether the copper tube hue is a standard hue.

[0084] For example, if the standard color tone is set to red, as the welded copper pipe is heated, the peak of the color tone curve in the HSV histogram obtained from the first monitoring image gradually approaches the red area, indicating that the color tone of the current welded copper pipe is gradually turning red, approaching the standard color tone, and a normal temperature result can be obtained at this time. However, if the welded copper pipe continues to be heated, the peak of the color tone curve in the HSV histogram obtained from the first monitoring image gradually moves away from the red area and approaches the yellow area, indicating that the color of the copper pipe is gradually turning orange-red, moving away from the standard color tone, and an abnormal temperature result can be obtained at this time.

[0085] In one feasible embodiment of this application, in order to enable the welder to better control the temperature of the copper tube during the heating process, prompting information can be generated adaptively based on the temperature detection results, thereby prompting the welder to adjust the welding flame to control the welding temperature.

[0086] S3: Continuously acquire the second monitoring image; wherein, the second monitoring image is a welding flame image during the welding process after the addition of solder;

[0087] Specifically, the camera device sends the entire process of copper pipe welding to the computer processing device in real time. The computer processing device uses image region segmentation to separate the copper pipe welding area and the welding flame area from the entire process video of copper pipe welding. The image set obtained from the welding flame area is used as the second monitoring image.

[0088] S4: Real-time detection of welding defects during the welding process based on the second monitoring image, and determination of the welding defect detection results; wherein, welding defects include at least sand hole defects and porosity defects;

[0089] Specifically, welding defects include pinhole defects and porosity defects. The welding defects during the welding process are detected in real time based on the second monitoring image, including the detection of pinhole defects and porosity defects. When detecting pinhole defects, the welding defect detection result can be determined as either a pinhole-containing result or a non-pinhole-containing result; when detecting porosity defects, the welding defect detection result can be determined as either a porosity-containing result or a non-porosity-containing result.

[0090] In one feasible embodiment of this application, the detection of trachoma defects based on the second monitoring image can be performed through the following steps:

[0091] Based on the second monitoring image, determine whether the welding flame simultaneously produces white smoke and white light;

[0092] When both white smoke and white light are present in the welding flame, the test result for trachoma defects is determined to be trachoma.

[0093] If the welding flame does not simultaneously produce white smoke and white light, the trachoma defect detection result is determined to be no trachoma.

[0094] Specifically, after adding solder to the copper pipe, the welding flame continuously heats the solder. When the temperature gets too high, the phosphorus in the solder will volatilize and burn. At this time, the combustion of phosphorus will produce white smoke and bright white light (such as...). Figure 3 As shown in the image "Welding flame that causes pinhole defects", if welding continues at the inherent temperature, pinholes will appear on the welded copper pipe after welding, which are many tiny voids, causing the welded copper pipe to be scrapped directly.

[0095] Therefore, during the welding process, detecting whether the welding flame simultaneously produces white smoke and white light can help determine whether the welded copper pipe will develop pinhole defects after welding.

[0096] In one feasible embodiment of this application, in order to accurately determine whether the welding flame simultaneously produces white smoke and white light, the type of pixels in the second monitoring image can be identified. In this embodiment, determining whether the welding flame simultaneously produces white smoke and white light can be achieved through the following steps:

[0097] Convert the second monitoring image to a grayscale image;

[0098] A grayscale image is segmented using a segmentation threshold to identify white pixel blocks within the image; the segmentation threshold is determined based on the pixel values ​​of the pixels in the grayscale image.

[0099] When a white pixel block is detected, the type of the white pixel block is determined based on its brightness; the type of the white pixel block is either a white smoke pixel block or a white light pixel block.

[0100] When both white smoke pixel blocks and white light pixel blocks are detected simultaneously, it is determined that the welding flame produces both white smoke and white light at the same time.

[0101] If white smoke pixel blocks and white light pixel blocks are not detected simultaneously, it is determined that the welding flame does not produce white smoke and white light at the same time.

[0102] Specifically, the second monitoring image is converted into a grayscale image, and the pixel value of each pixel in the grayscale image is determined. A segmentation threshold is determined based on the pixel values ​​of each pixel in the grayscale image; the segmentation threshold can be the average of the pixel values ​​of each pixel in the grayscale image. Color threshold segmentation is performed based on the segmentation threshold, identifying multiple white pixel blocks in the grayscale image, where the pixel values ​​of all pixels in the white pixel blocks are greater than the segmentation threshold. The brightness of each white pixel block is determined; white pixel blocks with brightness greater than the brightness threshold are identified as white light pixel blocks, and white pixel blocks with brightness less than the brightness threshold are identified as white smoke pixel blocks (the white light brightness of phosphorus volatilization combustion is the highest, the brightness of the flame itself is intermediate, and the brightness of smoke is the lowest). If both white smoke pixel blocks and white light pixel blocks are identified simultaneously, it is determined that the welding flame simultaneously produces white smoke and white light; if neither white smoke pixel blocks nor white light pixel blocks are identified simultaneously, it is determined that the welding flame does not simultaneously produce white smoke and white light.

[0103] Understandably, by identifying white pixel blocks in the grayscale image of the second monitoring image, the current welding flame and the surrounding white area were actually located. Based on the different brightness of white smoke and white light, the welding flame and the surrounding white area were further identified as either white smoke or white light.

[0104] In one feasible embodiment of this application, in order to enable welders to adjust the welding flame in a timely manner when white light and white smoke appear, adaptive prompting information can be generated based on the results of pinhole defect detection to prompt welders to adjust the welding flame. For example, when white light and white smoke appear simultaneously in the welding flame, a prompting information is generated to prompt welders to lower the temperature of the welding flame to prevent the volatilization of phosphorus in the solder, thereby avoiding the formation of pinhole defects.

[0105] In one feasible embodiment of this application, the detection of porosity defects based on the second monitoring image can be performed through the following steps:

[0106] Determine whether the welding flame is a reducing flame based on the second monitoring image;

[0107] When the welding flame is a reducing flame, the porosity defect detection result is determined to be a porosity result;

[0108] When the welding flame is not a reducing flame, the porosity defect detection result is determined to be a no-porosity result.

[0109] Specifically, a normal welding flame is a transparent blue. During welding, the welding material generates a large amount of gas, such as hydrogen and carbon dioxide, due to the heating effect of the welding flame. When these gases are not effectively vented and simultaneously combust, oxygen is consumed, producing water vapor and carbon dioxide. This results in insufficient oxygen in the welding flame, leading to a reducing flame, where the flame color changes from blue to yellow or orange, and the flame becomes cloudy. Simultaneously, the instantaneous heating of the generated water vapor causes the flame to enlarge instantly, its shape becoming much larger. (e.g.) Figure 3 As shown in the section on "Welding Flames that Cause Porosity Defects," if the generation of reducing flames is not intervened in time, it will lead to porosity in the welded copper tube after welding, affecting the material properties.

[0110] Therefore, during the welding process, by detecting whether the welding flame suddenly increases in size, becomes cloudy, or remains blue, it is possible to determine whether the welding flame is a reducing flame, and thus whether the welded copper pipe will have porosity defects after welding.

[0111] In one feasible embodiment of this application, in order to accurately determine whether a welding flame is a reducing flame, the characteristics of the welding flame can be analyzed based on a second monitoring image. In this embodiment, determining whether a welding flame is a reducing flame can be achieved through the following steps:

[0112] The perimeter of the welding flame edge, the flame hue, and the flame texture are determined based on the second monitoring image; wherein, the perimeter of the flame edge is determined by edge detection, the flame hue is determined by the HSV histogram of the second monitoring image, and the flame texture is determined by the gray-level co-occurrence matrix.

[0113] If the perimeter of the flame edge is greater than the perimeter threshold, the flame color is not blue, and the flame texture is a murky flame, the welding flame is judged to be a reducing flame.

[0114] If the perimeter of the flame edge is less than or equal to the perimeter threshold, the flame color is blue, or the flame texture is transparent, the welding flame is determined to be a non-reducing flame.

[0115] Specifically, the perimeter of the welding flame edge is determined by edge detection. The edge of the welding flame is extracted by edge detection, and the perimeter of the welding flame edge is calculated. The flame hue of the welding flame can be determined based on the HSV histogram of the second monitoring image. The specific implementation method is similar to the method for determining the hue of the copper tube in the above embodiment, and will not be repeated here. The flame texture can be determined based on the gray-level co-occurrence matrix. The gray-level co-occurrence matrix is ​​an image processing and texture analysis technique used to quantify the statistical correlation between pixel gray values ​​in a digital image. It can help analyze the texture features of the image, such as image roughness, contrast, structure, etc. Since image texture analysis methods based on the gray-level co-occurrence matrix already exist in the prior art, they will not be repeated here.

[0116] By comparing the flame edge perimeter with a perimeter threshold, it is determined whether a sudden change has occurred in the flame edge perimeter. If the flame edge perimeter exceeds the perimeter threshold, it indicates a sudden increase in the current welding flame. The perimeter threshold can be determined by those skilled in the art based on the perimeter of a standard welding flame, or it can be determined based on the flame edge perimeter of welding flames at historical moments prior to the current moment. For example, in a video recording of the entire copper pipe welding process, two adjacent monitoring images P1 and P2 are obtained. The flame edge perimeter monitored in P1 is C1, and the flame edge perimeter monitored in P2 is C2. The perimeter threshold can then be set to C1+a, where 'a' can be set by those skilled in the art. When C2 is greater than C1+a, it can be considered that a sudden change has occurred in the flame edge perimeter, indicating a significant increase.

[0117] Understandably, if the current welding flame suddenly increases significantly and clearly shows a color other than blue and is relatively cloudy when the flame edge perimeter is greater than the perimeter threshold, the flame color is not blue, and the flame texture is a cloudy flame, then the welding flame can be considered to be a reducing flame. Conversely, if the current welding flame is relatively stable, clearly shows a blue color, and is relatively transparent when the flame edge perimeter is less than or equal to the perimeter threshold, the flame color is blue, or the flame texture is a transparent flame, then the welding flame can be considered to be a normal welding flame and not a reducing flame.

[0118] In one feasible embodiment of this application, in order to enable welders to adjust the welding flame in a timely manner when the welding flame exhibits a reducing flame, adaptive prompting information can be generated based on the porosity defect detection results, thereby prompting welders to adjust the welding flame. For example, when the welding flame exhibits a reducing flame, a prompting information is generated to remind welders to reduce the fuel output of the welding flame and reduce the welding speed, thereby avoiding the generation of porosity defects.

[0119] Figure 4 This is a schematic diagram of the overall process of a copper pipe welding detection method provided in this application embodiment. Based on all the above embodiments, the overall process of the copper pipe welding detection method provided in this application embodiment during specific implementation can be as follows:

[0120] At the start of the welding operation, a camera is activated to record the entire copper pipe welding process in real time. A first monitoring image is acquired from this video, and the copper pipe temperature is monitored based on this image. If the temperature reading is abnormal, the welder adjusts the welding flame and monitors the temperature again. If the temperature reading is normal, solder is added. After adding solder, a second monitoring image is acquired from the video, and pinhole defects are detected. If pinhole defects are detected, the welder adjusts the welding flame and monitors the temperature again. If no pinhole defects are detected, porosity defects are detected based on the second monitoring image. If porosity is detected, the welder adjusts the welding flame and monitors the temperature again. If no porosity is detected, the entire copper pipe welding process is monitored.

[0121] Understandably, the temperature of the copper tube is continuously monitored during the heating process until the welder adds solder. During welding, pinhole and porosity defects are simultaneously and continuously detected until the welder finishes the welding operation.

[0122] The technical solution provided in this application enables real-time detection of copper pipe temperature via copper pipe image during heating and real-time detection of welding flame via flame image during welding, generating corresponding detection results in real time. This achieves full-process monitoring of copper pipe welding and enables detection of copper pipe welding quality during the welding process.

[0123] Corresponding to the above method embodiments, this application also provides a detection device for copper pipe welding. Figure 5 This is a schematic diagram of the structure of a copper pipe welding detection device provided in an embodiment of this application, with reference to... Figure 5 The copper pipe welding detection device provided in this application specifically includes:

[0124] The first acquisition module 501 is used to continuously acquire a first monitoring image; wherein, the first monitoring image is an image of the copper tube during the heating process before the addition of solder;

[0125] The first detection module 502 is used to detect the temperature of the copper tube in real time during the heating process based on the first monitoring image, and determine the detection result of the copper tube temperature.

[0126] The second acquisition module 503 is used to continuously acquire the second monitoring image; wherein the second monitoring image is a welding flame image during the welding process after the addition of solder;

[0127] The second detection module 504 is used to perform real-time detection of welding defects during the welding process based on the second monitoring image and determine the welding defect detection result; wherein the welding defects include at least sand hole defects and porosity defects.

[0128] In one feasible embodiment of this application, the copper tube temperature detection result is either a normal temperature result or a temperature abnormal result, and the first detection module 502 includes:

[0129] The first judgment unit is used to determine whether the copper tube color is the standard color during the heating process based on the first monitoring image.

[0130] The first determining unit is used to determine that the copper tube temperature detection result is a normal temperature result when the copper tube color tone is the standard color tone.

[0131] The second determining unit is used to determine that the copper tube temperature detection result is an abnormal temperature result when the copper tube color tone is not the standard color tone.

[0132] In one feasible embodiment of this application, the first determination unit includes:

[0133] The first conversion subunit is used to convert the first monitoring image from RGB color space to HSV color space, thereby determining the HSV histogram of the first monitoring image and determining the hue curve in the HSV histogram; wherein, the vertical axis of the HSV histogram represents the frequency of hue occurrence, and the horizontal axis of the HSV histogram represents the hue.

[0134] The first determining subunit is used to determine the maximum hue frequency based on the hue curve, determine the hue corresponding to the maximum hue frequency in the HSV histogram, and determine whether the hue corresponding to the maximum hue frequency is within the hue range corresponding to the standard hue.

[0135] The first judgment subunit is used to determine that the copper tube hue is the standard hue during the heating process if the hue corresponding to the maximum hue frequency is within the hue range corresponding to the standard hue.

[0136] The second judgment subunit is used to determine that the copper tube hue is not a standard hue during the heating process if the hue corresponding to the maximum hue frequency is not within the hue range corresponding to the standard hue.

[0137] In one feasible embodiment of this application, the welding defect detection result includes the trachoma defect detection result, which is either a trachoma detection result or a no-trachoma detection result. The second detection unit 504 includes:

[0138] The second judgment unit is used to determine whether the welding flame simultaneously produces white smoke and white light based on the second monitoring image;

[0139] The third determining unit is used to determine the trachoma defect detection result as having trachoma when white smoke and white light appear simultaneously in the welding flame.

[0140] The fourth determining unit is used to determine the trachoma defect detection result as no trachoma result when the welding flame does not simultaneously produce white smoke and white light.

[0141] In one feasible embodiment of this application, the second determination unit includes:

[0142] The second conversion subunit is used to convert the second monitoring image into a grayscale image;

[0143] The identification subunit is used to perform color threshold segmentation on the grayscale image using a segmentation threshold to identify white pixel blocks in the grayscale image; wherein, the segmentation threshold is determined based on the pixel value of the pixel in the grayscale image;

[0144] The second determining subunit is used to determine the type of white pixel block based on its brightness when a white pixel block is detected; wherein the type of white pixel block is either a white smoke pixel block or a white light pixel block.

[0145] The third judgment subunit is used to determine that the welding flame produces both white smoke and white light when both white smoke pixel blocks and white light pixel blocks are detected at the same time.

[0146] The fourth judgment subunit is used to determine that the welding flame does not produce white smoke and white light at the same time if the white smoke pixel block and the white light pixel block are not detected simultaneously.

[0147] In one feasible embodiment of this application, the welding defect detection result includes the porosity defect detection result, which is either a porosity result or a porosity-free result. The second detection module 504 includes:

[0148] The third judgment unit is used to determine whether the welding flame is a reducing flame based on the second monitoring image;

[0149] The fifth determining unit is used to determine the porosity defect detection result as having porosity when the welding flame is a reducing flame.

[0150] The sixth determining unit is used to determine the porosity defect detection result as a porosity-free result when the welding flame is not a reducing flame.

[0151] In one feasible embodiment of this application, the third determination unit includes:

[0152] The third determining subunit is used to determine the perimeter of the flame edge, the flame hue, and the flame texture of the welding flame based on the second monitoring image; wherein, the perimeter of the flame edge is determined by edge detection, the flame hue is determined by the HSV histogram of the second monitoring image, and the flame texture is determined by the gray-level co-occurrence matrix.

[0153] The fifth judgment subunit is used to determine that the welding flame is a reducing flame when the perimeter of the flame edge is greater than the perimeter threshold, the flame color is not blue, and the flame texture is a turbid flame.

[0154] The sixth judgment subunit is used to determine that the welding flame is not a reducing flame when the perimeter of the flame edge is less than or equal to the perimeter threshold, the flame color is blue, or the flame texture is a transparent flame.

[0155] like Figure 6 As shown in the figure, this application provides an air conditioner control device, including a processor 601, a communication interface 602, a memory 603, and a communication bus 604. The processor 601, communication interface 602, and memory 603 communicate with each other via the communication bus 604.

[0156] Memory 603 is used to store computer programs;

[0157] In one embodiment of this application, the processor 601, when executing a program stored in the memory 603, implements a copper pipe welding detection method provided in any of the foregoing method embodiments, including:

[0158] The first monitoring image is continuously acquired; wherein, the first monitoring image is an image of the copper tube during the heating process before the addition of solder;

[0159] The temperature of the copper tube during the heating process is detected in real time based on the first monitoring image, and the detection result of the copper tube temperature is determined.

[0160] The second monitoring image is continuously acquired; wherein, the second monitoring image is a welding flame image during the welding process after the addition of solder;

[0161] Welding defects during the welding process are detected in real time based on the second monitoring image to determine the detection results; among which, welding defects include at least sand hole defects and porosity defects.

[0162] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of a copper pipe welding detection method as provided in any of the foregoing method embodiments.

[0163] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0164] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0165] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0166] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for detecting copper pipe welding, characterized in that, The method includes: Continuously acquire the first monitoring image; wherein, the first monitoring image is an image of the copper tube during the heating process before the addition of solder; The temperature of the copper tube during the heating process is detected in real time based on the first monitoring image, and the detection result of the copper tube temperature is determined. Continuously acquire a second monitoring image; wherein the second monitoring image is a welding flame image during the welding process after the addition of solder; The welding defects in the welding process are detected in real time based on the second monitoring image to determine the welding defect detection result; wherein the welding defects include at least sand hole defects and porosity defects; The welding defect detection results include trachoma defect detection results, which are either trachoma present or trachoma absent. The welding defects during the welding process are detected in real-time based on the second monitoring image to determine the welding defect detection results, including: determining whether the welding flame simultaneously produces white smoke and white light based on the second monitoring image; if the welding flame simultaneously produces white smoke and white light, the trachoma defect detection result is determined to be trachoma present; if the welding flame does not simultaneously produce white smoke and white light, the trachoma defect detection result is determined to be trachoma absent.

2. The method according to claim 1, characterized in that, The copper tube temperature detection result is either a normal temperature result or an abnormal temperature result. The copper tube temperature is detected in real time during the heating process based on the first monitoring image to determine the copper tube temperature detection result, including: Based on the first monitoring image, determine whether the copper tube color tone is the standard color tone during the heating process; If the copper tube color tone is the standard color tone, the copper tube temperature detection result is determined to be the normal temperature result; If the copper tube color tone is not the standard color tone, the copper tube temperature detection result is determined to be the temperature anomaly result.

3. The method according to claim 2, characterized in that, Determining whether the copper tube's color tone is the standard color tone during the heating process based on the first monitoring image includes: The first monitoring image is converted from RGB color space to HSV color space to determine the HSV histogram of the first monitoring image, and the hue curve is determined in the HSV histogram; wherein, the vertical axis of the HSV histogram represents the frequency of hue occurrence, and the horizontal axis of the HSV histogram represents the hue. The maximum hue frequency is determined based on the hue curve. The hue corresponding to the maximum hue frequency is determined in the HSV histogram. It is then determined whether the hue corresponding to the maximum hue frequency is within the range of the hue corresponding to the standard hue. If the hue corresponding to the maximum hue frequency is within the hue range corresponding to the standard hue, it is determined that the hue of the copper tube during the heating process is the standard hue; If the hue corresponding to the maximum hue frequency is not within the range of the hue corresponding to the standard hue, it is determined that the hue of the copper tube is not the standard hue during the heating process.

4. The method according to claim 1, characterized in that, Determining whether the welding flame simultaneously produces white smoke and white light based on the second monitoring image includes: Convert the second monitoring image into a grayscale image; The grayscale image is segmented by a segmentation threshold to identify white pixel blocks in the grayscale image; wherein the segmentation threshold is determined based on the pixel value of the pixel in the grayscale image. If the white pixel block is detected, the type of the white pixel block is determined based on its brightness; wherein the type of the white pixel block is either a white smoke pixel block or a white light pixel block. If both the white smoke pixel block and the white light pixel block are detected simultaneously, it is determined that the welding flame produces both white smoke and white light. If the white smoke pixel block and the white light pixel block are not detected simultaneously, it is determined that the welding flame does not produce white smoke and white light at the same time.

5. The method according to claim 1, characterized in that, The welding defect detection results include porosity defect detection results, which are either porosity present or porosity absent. The welding defects during the welding process are detected in real time based on the second monitoring image to determine the welding defect detection results, including: Determine whether the welding flame is a reducing flame based on the second monitoring image; When the welding flame is the reducing flame, the porosity defect detection result is determined to be the porosity result; If the welding flame is not the reducing flame, the porosity defect detection result is determined to be the no-porosity result.

6. The method according to claim 5, characterized in that, Determining whether the welding flame is a reducing flame based on the second monitoring image includes: The perimeter of the welding flame edge, the flame hue, and the flame texture are determined based on the second monitoring image; wherein, the perimeter of the flame edge is determined by edge detection, the flame hue is determined by the HSV histogram of the second monitoring image, and the flame texture is determined by the gray-level co-occurrence matrix; If the perimeter of the flame edge is greater than the perimeter threshold, the flame hue is not blue, and the flame texture is a cloudy flame, then the welding flame is determined to be a reducing flame. If the perimeter of the flame edge is less than or equal to the perimeter threshold, the flame hue is blue, or the flame texture is transparent, then the welding flame is determined not to be a reducing flame.

7. A detection device for copper pipe welding, characterized in that, The device includes: The first acquisition module is used to continuously acquire a first monitoring image; wherein, the first monitoring image is an image of the copper tube during the heating process before the addition of solder; The first detection module is used to detect the temperature of the copper tube during the heating process in real time based on the first monitoring image, and determine the copper tube temperature detection result. The second acquisition module is used to continuously acquire the second monitoring image; wherein the second monitoring image is a welding flame image during the welding process after the addition of solder; The second detection module is used to perform real-time detection of welding defects in the welding process based on the second monitoring image, and determine the welding defect detection result; wherein, the welding defects include at least sand hole defects and porosity defects; The welding defect detection results include trachoma defect detection results, which are either trachoma present or trachoma absent. The second detection unit includes: a second judgment unit, used to judge whether the welding flame simultaneously produces white smoke and white light based on the second monitoring image; a third determination unit, used to determine that the trachoma defect detection result is trachoma present when the welding flame simultaneously produces white smoke and white light; and a fourth determination unit, used to determine that the trachoma defect detection result is trachoma absent when the welding flame does not simultaneously produce white smoke and white light.

8. An electronic device, characterized in that, include: At least one communication interface; At least one bus connected to the at least one communication interface; At least one processor connected to the at least one bus; At least one memory connected to the at least one bus, wherein the processor is configured to perform the method as described in any one of claims 1-6.

9. A computer storage medium, characterized in that, The device stores computer-executable instructions for performing the method as described in any one of claims 1-6.

Images