Blast lamp detection system

Abstract

The invention relates to a blowtorch detection system, which comprises a detection mechanism, the detection mechanism comprises an image acquisition unit, an image processing unit and a control unit, and the image acquisition unit is used for directly facing a jet end face of a blowtorch to acquire an image of a blowtorch hole; the image processing unit is connected with the image acquisition unit and is used for processing the acquired image so as to obtain quality parameters of each blowtorch hole; the control unit is connected with the image processing unit and compares the blow lamp hole qualified threshold value with the quality parameters of the blow lamp holes so as to determine whether each blow lamp hole is qualified or not. The problem that the quality inspection effect of the blowtorch is poor in the prior art can be solved.

Description

Technical Field

[0001] This application relates to the technical field of optical fiber preform manufacturing, and particularly to a burner detection system. Background Art

[0002] The main quality indicators of OVD deposited powder rods mainly focus on the outer diameter uniformity of the loose body soot, the number and size of bright spots on the surface of the powder rod, the bow of the powder rod, etc. When the extreme difference of the outer diameter of the powder rod is large, it may lead to the exceeding of the diameter ratio of the cladding / core of the sintered optical rod. At the same time, the exceeding of the number of surface bright spots and the bow will cause the product to be unqualified and scrapped. The outer diameter uniformity, surface bright spots, flame abnormality and the burner have a great impact. Whether the working state of the burner is normal is crucial. The following points will affect the normal working of the burner: (1) The processing dimensions of the burner do not meet the requirements, such as the outer diameter exceeding the standard, burrs, etc.; (2) High temperature causes the burner holes to deform; (3) The wear of the cleaning brush for cleaning the burner mouth causes the burner holes to deform; (4) The collision caused by repeated installation causes the burner holes to deform.

[0003] The deformation of the material tube caused by long-term high-temperature environment, cleaning and collision will directly affect the spraying effect of the burner, may cause the flame to deform, resulting in abnormal outer diameter of the deposited powder rod at the deposition point. At the same time, the burner air holes will deform due to heat, causing octamethylcyclotetrasiloxane D4 to react in advance to form dust, which accumulates at the material tube mouth to form burrs. The burr phenomenon not only affects the deposition effect, but also a large number of bright spots will be generated when the dust floats onto the rod body.

[0004] The disassembly and installation of the burner are very complicated. The general on-site inspection method is to observe the surface of the burner with eyes. However, the burner air holes are very small and cannot be detected unless there is obvious deformation, which will lead to frequent occurrence of flame abnormality.

[0005] In short, on the one hand, there is no good detection method to judge whether the processing of the burner is qualified after processing. Only the plug gauge is used to detect whether the diameter of the burner hole meets the requirements, and the workload is large. Taking the OVD deposition burner as an example, each burner has 3 specifications and a total of 170 holes, and 2 types of plug gauges are required for each hole. More importantly, although the burrs are removed manually, the tiny burrs that cannot be identified by the naked eye cannot be detected.

[0006] On the other hand, the deformation of the material tube caused by long-term high-temperature environment, cleaning and collision will directly affect the spraying effect of the burner. However, on-site inspection can only find problems through routine inspection and regular inspection. Routine inspection usually observes the surface of the burner with eyes first. However, the burner air holes are very small and cannot be detected unless there is obvious deformation. And regular inspection requires the disassembly of the burner for inspection, which is not only time-consuming, but also the disassembly process will cause flame abnormality due to human reasons such as improper installation of the sealing ring.

[0007] In addition, abnormal flame phenomena are common during the production of optical fiber preforms, usually caused by unclean material tubes, gel formation due to raw material problems, or deformation of the burner holes or damage to the burner seals. Once an abnormal flame occurs, on-line intervention is impossible, and production can only be terminated, resulting in product scrapping. Summary of the Invention

[0008] An embodiment of the present application provides a burner detection system to solve the problem of poor inspection effect of burner quality in related technologies.

[0009] An embodiment of the present application provides a burner detection system, which includes a detection mechanism. The detection mechanism includes:

[0010] An image acquisition unit, which is used to collect an image of the burner holes facing the injection end face of the burner;

[0011] An image processing unit, which is connected to the image acquisition unit and is used to process the collected image to obtain the quality parameters of each burner hole;

[0012] A control unit, which is connected to the image processing unit and compares the qualified threshold of the burner holes with the quality parameters of the burner holes to determine whether each burner hole is qualified.

[0013] In some embodiments, the quality parameter of the burner hole includes the difference between the maximum and minimum inner diameters of the burner hole in different directions obtained by processing;

[0014] When the difference is greater than the qualified threshold of the burner hole, the burner hole is deformed and unqualified.

[0015] In some embodiments, the quality parameter of the burner hole includes an area ratio, which is the ratio of the area of the region where the processed burner hole exceeds the boundary of the standard circular burner hole to the area of the standard circular burner hole when the center of the processed burner hole coincides with the center of the standard circular burner hole;

[0016] When the area ratio is greater than the qualified threshold of the burner hole, the burner hole is deformed and unqualified.

[0017] In some embodiments, the quality parameter of the burner hole includes the gray value of the processed burner hole. When the gray value is less than the qualified threshold of the burner hole, there is foreign matter in the burner hole and it is unqualified;

[0018] Alternatively, the quality parameter of the burner hole includes the ratio of the area of the dark gray part to the total area of the rectangular area obtained by unfolding the processed burner hole. When the ratio is greater than the qualified threshold of the burner hole, there is foreign matter in the burner hole and it is unqualified.

[0019] In some embodiments, it further includes:

[0020] A first base for carrying a blowtorch, and a light source for irradiating along the axial direction of the blowtorch is arranged on the first base;

[0021] A guide rail;

[0022] A moving bracket on which the image acquisition unit is installed;

[0023] A driving unit connected to the moving bracket and used to drive the moving bracket to move on the guide rail to approach or move away from the first base;

[0024] Wherein, the control unit is connected to the driving unit and used to control the operation of the driving unit.

[0025] In some embodiments, the control unit prestores the focusing positions corresponding to different types of blowtorches, and the focusing position is the position where the moving bracket moves from the starting point of the guide rail to make the blowtorch be at the focus of the image acquisition unit;

[0026] The control unit is further used to receive the type of the blowtorch and drive the moving bracket to move to the corresponding focusing position.

[0027] In some embodiments, it further includes:

[0028] An AGV cart;

[0029] A second base installed on the AGV cart;

[0030] A robot installed on the second base, and the image acquisition unit is carried on the arm of the robot;

[0031] And, the control unit is further connected to the image acquisition unit, the AGV cart and the robot, and is used to control the AGV cart to move in front of the blowtorch device to a preset positioning point, according to the robot coordinates of the blowtorch pre-calibrated in the robot coordinate system, control the robot to move the image acquisition unit above the blowtorch to make the blowtorch be at the robot coordinate, and control the image acquisition unit to take a picture, wherein the blowtorch device includes several blowtorches.

[0032] In some embodiments, it includes:

[0033] A blowtorch off-line static detection device, which includes:

[0034] - The detection mechanism;

[0035] - A first base for carrying a blowtorch, with a light source for irradiating along the axial direction of the blowtorch provided on the first base;

[0036] - A guide rail;

[0037] - A moving bracket on which the image acquisition unit is installed;

[0038] - A driving unit connected to the moving bracket and used to drive the moving bracket to move on the guide rail to approach or move away from the first base; wherein, the control unit is connected to the driving unit and used to control the driving unit to work;

[0039] An on-line dynamic detection device for a blowtorch, which includes:

[0040] - The detection mechanism;

[0041] - An AGV cart;

[0042] - A second base installed on the AGV cart;

[0043] - A robot installed on the second base, and the image acquisition unit is carried on the arm of the robot; wherein, the control unit is also connected to the image acquisition unit, the AGV cart and the robot, and is used to control the AGV cart to move in front of the blowtorch equipment to a preset positioning point, and according to the robot coordinates of the blowtorch calibrated in advance in the robot coordinate system, control the robot to move the image acquisition unit above the blowtorch so that the blowtorch is in the robot coordinates, and control the image acquisition unit to take pictures, wherein the blowtorch equipment includes several blowtorches.

[0044] In some embodiments, the image acquisition unit is also used to acquire the flame image when the blowtorch is working;

[0045] The image processing unit is also used to process the flame image to obtain the pixel area of the flame region;

[0046] The control unit is also used to compare the pixel area of the flame region with the pixel area value range. If it is within the pixel area value range, the flame is normal, otherwise, the flame is abnormal.

[0047] In some embodiments, the image acquisition unit is also used to acquire the color flame image when the blowtorch is working;

[0048] The image processing unit is also used to process the acquired color flame image to obtain the R value ratio, G value ratio and B value ratio in the color flame image;

[0049] The control unit is further configured to compare the proportion of the R value, the proportion of the G value, and the proportion of the B value in the color flame image with the R value proportion value range, the G value proportion value range, and the B value proportion value range respectively. If they are all within the corresponding value ranges, the flame is normal; otherwise, the flame is abnormal.

[0050] The beneficial effects brought by the technical solution provided in this application include:

[0051] In this application, an image acquisition unit is used to acquire an image of a blowtorch, and then an image processing unit performs image processing on the acquired image, so that quality parameters that can be used to characterize whether the blowtorch holes are qualified can be obtained. By comparing the quality parameters with a pre-set qualified threshold for the blowtorch holes, it can be determined whether each blowtorch hole is qualified. Compared with visual inspection or using a large number of plug gauges for detection, the detection method using image processing means in this application can not only detect defects that cannot be recognized by the human eye, with high detection accuracy and good detection effect, but also does not require a large number of plug gauges, with a small detection workload and high detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0053] Figure 1 Schematic diagram of the offline static detection device for a blowtorch provided by an embodiment of the present application;

[0054] Figure 2 Schematic diagram when the blowtorch holes obtained by processing in an embodiment of the present application coincide with the centers of standard circular blowtorch holes;

[0055] Figure 3 Gray-scale image after image processing provided by an embodiment of the present application;

[0056] Figure 4 Blowtorch hole expansion diagram provided by an embodiment of the present application;

[0057] Figure 5 Online dynamic detection device for a blowtorch provided by an embodiment of the present application;

[0058] Figure 6 Gray-scale image of the flame image provided by an embodiment of the present application.

[0059] In the figure: 1. Image acquisition unit; 2. Blowtorch; 3. First base; 4. Guide rail; 5. Moving bracket; 6. Driving unit; 7. AGV cart; 8. Second base; 9. Robot. Specific Embodiments

[0060] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are some, but not all, of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts shall fall within the scope of protection of this application.

[0061] Referring to Figure 1 As shown, the embodiment of this application provides a blowtorch detection system, which includes a detection mechanism. The detection mechanism includes an image acquisition unit 1, an image processing unit, and a control unit. The image acquisition unit 1 can use a camera. To ensure that the detection accuracy meets the requirement of ±0.01 mm, a high-pixel gigabit area array camera can be selected, and a parallel optical path double telecentric lens is selected for the lens. This lens has the characteristics of high resolution, ultra-large depth of field, and ultra-low distortion, and is suitable for high-precision detection applications. The image acquisition unit 1 is used to face the spraying end face of the blowtorch 2 to acquire an image of the blowtorch holes. When in use, it takes a picture facing the spraying end face of the blowtorch 2, so that an image of the spraying end face containing all the blowtorch holes can be taken; the image processing unit is connected to the image acquisition unit 1 and is used to process the acquired image to obtain the quality parameters of each blowtorch hole; the control unit is connected to the image processing unit and compares the qualified threshold of the blowtorch holes with the quality parameters of the blowtorch holes to determine whether each blowtorch hole is qualified.

[0062] In this application, the image of the blowtorch is acquired by the image acquisition unit, and then the acquired image is processed by the image processing unit, so that the quality parameters that can be used to characterize whether the blowtorch holes are qualified can be obtained. The quality parameters are compared with the pre-set qualified threshold of the blowtorch holes, so that it can be determined whether each blowtorch hole is qualified. Compared with visual inspection or using a large number of plug gauges for detection, this application uses image processing means for detection, which can not only detect defects that cannot be recognized by the human eye, has high detection accuracy and good detection effect, but also does not require a large number of plug gauges, has a small detection workload, and high detection efficiency.

[0063] As an example, to determine whether the blowtorch holes are deformed, the quality parameters of the blowtorch holes include the difference between the maximum and minimum inner diameters of the blowtorch holes in different directions obtained by processing; when the difference is greater than the qualified threshold of the blowtorch holes, the blowtorch holes are deformed and unqualified, otherwise, the blowtorch holes are not deformed.

[0064] In this example, the torch hole is processed by an image processing unit, so that the inner diameters of the torch hole in different directions can be obtained, and the maximum and minimum inner diameters are found. Then, the difference between the two can be calculated. At this time, a qualified threshold for the torch hole (i.e., the difference threshold at this time) can be preset. If it exceeds, it means that the major axis and minor axis of the torch hole differ greatly, the hole is deformed greatly, exceeding the expected acceptable range, and it is judged as unqualified. If it does not exceed, it means that the major axis and minor axis of the torch hole differ little. Although the hole has a certain deformation, it is within the expected acceptable range, so it is judged as not deformed.

[0065] As another example, to determine whether the torch hole is deformed, the identified torch hole can also be compared with a standard hole to judge whether it is deformed.

[0066] Specifically, the quality parameter of the torch hole includes the area ratio. The area ratio is the ratio of the area of the region where the processed torch hole exceeds the boundary of the standard circular torch hole to the area of the standard circular torch hole when the center of the processed torch hole coincides with the center of the standard circular torch hole. When the area ratio is greater than the qualified threshold of the torch hole, the torch hole is deformed and unqualified.

[0067] In this example, see Figure 2 As shown in the figure, the figure in the upper right corner is the standard circular torch hole, whose center is at point A, and the figure in the upper left corner is the processed torch hole, whose center is at point B. Adjust the center positions of the two until they coincide. At this time, the regions where the processed torch hole exceeds the boundary of the standard circular torch hole are the gray regions on the left and right. Calculate the ratio of the area of this gray region to the area of the standard circular torch hole. At this time, a qualified threshold for the torch hole (i.e., the area ratio at this time) can be preset. If it exceeds, it means that the torch hole is deformed greatly, exceeding the expected acceptable range, and it is judged as unqualified. If it does not exceed, it means that the torch hole has a certain deformation, but it is within the expected acceptable range, so it is judged as not deformed.

[0068] In fact, the area of the overlapping part between the standard circular torch hole and the processed torch hole can also be judged. The smaller this area is, the greater the deformation is. By comparing the ratio of the area of the overlapping part to the area of the standard circular torch hole with a qualified threshold of the torch hole, it can also be judged whether there is deformation.

[0069] It can be seen that through image processing, not only obvious deformations can be detected, but also deformations that are imperceptible to the naked eye can be detected.

[0070] During the processing of the blowtorch, burrs may exist in the blowtorch holes due to processing problems, or burrs or foreign matters such as gels may appear after spraying during the production of the optical fiber preform. To determine whether there are foreign matters in the blowtorch holes, as an example, the quality parameter of the blowtorch holes includes the gray value of the blowtorch holes obtained through processing; when the gray value is less than the qualified threshold of the blowtorch holes, there are foreign matters in the blowtorch holes and it is unqualified.

[0071] In this example, refer to Figure 3 As shown, it is a gray-scale image after image processing, where the white area is the blowtorch hole. The blowtorch hole is composed of pixel points one by one. Since it is white, the gray value of its pixel points is relatively high. When foreign matters appear in the blowtorch hole, the foreign matter area appears gray or black because light cannot pass through, and the gray value of its pixel points is relatively low. If there are foreign matters, it will lower the average value of the gray values of each pixel point in the area where the blowtorch hole is located. Therefore, the sum of the gray values of all pixel points in the area where the blowtorch hole is located can be calculated, and then the average value is calculated as the gray value of the blowtorch hole. At this time, a qualified threshold (which is the gray value at this time) of the blowtorch hole can be preset. If it is less than this value, there are foreign matters; otherwise, there are no foreign matters.

[0072] It can be understood that when it is determined that the blowtorch hole is deformed, the deformed blowtorch hole can be marked in the image. Similarly, when it is determined that there are foreign matters in the blowtorch hole, the blowtorch hole with foreign matters can be marked in the image, which is convenient for corresponding to the actual hole positions on the blowtorch.

[0073] As another example, to determine whether there are foreign matters, specifically, the quality parameter of the blowtorch hole includes the ratio of the area of the black-gray part to the total area of the rectangular area obtained by unfolding the blowtorch hole obtained through processing. When this ratio is greater than the qualified threshold of the blowtorch hole (which is an area ratio at this time), there are foreign matters in the blowtorch hole and it is unqualified.

[0074] In this example, refer to Figure 4 As shown, the blowtorch hole is cylindrical and becomes rectangular after unfolding. In the rectangular area, if burrs, gels and other foreign matters are black-gray, the ratio of the area of the black-gray part to the total area of the rectangular area is statistically calculated. If it exceeds the qualified threshold of the blowtorch hole, it means there are foreign matters in the blowtorch hole and it is unqualified. Otherwise, it is qualified.

[0075] Refer to Figure 1As shown, the blowtorch detection system can be used as an off-line static detection device for blowtorches. At this time, the blowtorch detection system further includes a first base 3, a guide rail 4, and a driving unit 6. The first base 3 is used to carry the blowtorch 2, and a light source for irradiating along the axial direction of the blowtorch 2 is arranged on the first base 3; the image acquisition unit 1 is installed on the moving bracket 5; the driving unit 6 is connected to the moving bracket 5 and is used to drive the moving bracket 5 to move on the guide rail 4 to approach or move away from the first base 3. The driving unit 6 can use a servo motor, and the driving unit 6 can be connected to the moving bracket 5 through a ball screw; wherein, the control unit is connected to the driving unit 6 and is used to control the driving unit 6 to work.

[0076] It can be understood that during installation, ensure that the central axis of the image acquisition unit 1 is coaxial with the central axis of the blowtorch 2 carried on the first base 3. As Figure 1 shown, during shooting, the light source irradiates the blowtorch 2 along the axial direction of the blowtorch 2, and the light passes through the blowtorch holes and exits. At this time, the image acquisition unit 1 can shoot directly at the blowtorch 2 against the light, avoiding the blowtorch holes appearing elliptical due to shooting angle problems.

[0077] The driving unit 6 drives the moving bracket 5 to move, so that the image acquisition unit 1 can adjust the shooting position to keep the clarity of the captured image optimal.

[0078] In order to achieve automatic focusing shooting, the control unit pre-stores the focusing positions corresponding to different types of blowtorches 2. The focusing position is the position where the moving bracket 5 moves from the starting point of the guide rail 4 to make the blowtorch 2 be at the focus of the image acquisition unit 1; the control unit is also used to receive the type of the blowtorch 2 and drive the moving bracket 5 to move to the corresponding focusing position.

[0079] For different types of blowtorches 2, the blowtorch 2 can be first placed on the first base 3 and ensured to be placed correctly, and then the moving bracket 5 can be manually adjusted to start moving from the starting point of the guide rail 4 until the blowtorch 2 is at the focus of the image acquisition unit 1. At this time, the clarity of the shooting field of view is kept optimal, and the position of the moving bracket 5 at this time is recorded and used as the focusing position of this blowtorch 2. By analogy, the focusing positions corresponding to different types of blowtorches 2 are calibrated. Subsequently, during application, the type of the blowtorch 2 to be measured can be input or selected, and the control unit will automatically adjust the focus according to the input or selected type of the blowtorch 2.

[0080] It can be understood that after shooting, the control unit can also drive the moving bracket 5 to reset to the starting point of the guide rail 4 and wait for the next shooting.

[0081] It can be understood that the control unit can be connected to the image acquisition unit 1 to directly control the image acquisition unit 1 to shoot.

[0082] See Figure 5 As shown, the blowtorch detection system can be used as an on-line dynamic detection device for the blowtorch. At this time, the blowtorch detection system further includes an AGV cart 7, a second base 8, and a robot 9; a position map has been generated for the AGV cart 7 in advance according to the position information of each area in the factory for path planning and navigation. The second base 8 is installed on the AGV cart 7; the robot 9 is installed on the second base 8, and the image acquisition unit 1 is mounted on the arm of the robot 9. The robot 9 can move the arm according to needs through the controller to deliver the image acquisition unit 1 to the target position; the control unit is also connected to the image acquisition unit 1, the AGV cart 7, and the robot 9, and is used to control the AGV cart 7 to move in front of the blowtorch equipment to a preset positioning point, and according to the robot coordinates of the blowtorch 2 in the robot coordinate system, control the robot 9 to move the image acquisition unit 1 above the blowtorch 2 so that the blowtorch 2 is in the robot coordinates, and control the image acquisition unit 1 to take a picture.

[0083] Specifically, on the blowtorch equipment, there is a row of multiple blowtorches, such as Figure 5 there are seven blowtorches in a row, and the spacing between each blowtorch is a known quantity. A preset reference point can be set on the blowtorch equipment, and the relative position relationship between the preset reference point and one of the blowtorches is also a known quantity. For example, in Figure 5 the preset reference point is set on the left side of the leftmost blowtorch (denoted as blowtorch A, and blowtorches B, C, etc. are arranged in sequence to the right). Move the AGV cart 7 in front of the blowtorch equipment to the preset positioning point. That is, for the blowtorch equipment, it has a preset positioning point for the AGV cart 7 to locate. When the AGV cart 7 moves to the preset positioning point of the blowtorch equipment, stop. Then, drive the image acquisition unit 1 to move above blowtorch A through the robot 9, move up and down to adjust the focal length to the best position, and record the robot coordinates at this time. These robot coordinates are the coordinates of blowtorch A in the robot coordinate system. Then, drive the image acquisition unit 1 to move above blowtorch B through the robot 9, move up and down to adjust the focal length to the best position, and record the robot coordinates at this time. These robot coordinates are the coordinates of blowtorch B in the robot coordinate system. And so on, the coordinates of each blowtorch 2 in the robot coordinate system can be calibrated to obtain the pre-calibrated robot coordinates corresponding to each blowtorch 2. During subsequent detection, first move the AGV cart 7 to the preset positioning point of the blowtorch equipment, stop, and then control the movement of the robot 9 according to the pre-calibrated robot coordinates of each blowtorch 2, drive the image acquisition unit 1 to move above blowtorch A, and ensure that the coordinates of the blowtorch 2 in the robot coordinate system are the corresponding robot coordinates. At this time, take a picture.

[0084] Furthermore, the blowtorch detection system includes a blowtorch off-line static detection device and a blowtorch on-line dynamic detection device, which can be selected and used according to actual needs. Among them, the blowtorch off-line static detection device includes a detection mechanism, a first base 3, a guide rail 4, a moving bracket 5 and a driving unit 6; the first base 3 is used to carry the blowtorch 2, and a light source for irradiating along the axis of the blowtorch 2 is arranged on the first base 3; the image acquisition unit 1 is installed on the moving bracket 5; the driving unit 6 is connected to the moving bracket 5 and is used to drive the moving bracket 5 to move on the guide rail 4 to approach or move away from the first base 3; among them, the control unit is connected to the driving unit 6 and is used to control the driving unit 6 to work.

[0085] The blowtorch on-line dynamic detection device includes a detection mechanism, an AGV cart 7, a second base 8 and a robot 9; the second base 8 is installed on the AGV cart 7; the robot 9 is installed on the second base 8, and the image acquisition unit 1 is carried on the arm of the robot 9; among them, the control unit is also connected to the image acquisition unit 1, the AGV cart 7 and the robot 9, and is used to control the AGV cart 7 to move in front of the blowtorch device to a preset positioning point, and according to the robot coordinates of the blowtorch 2 in the robot coordinate system, control the robot 9 to move the image acquisition unit 1 above the blowtorch 2 so that the blowtorch 2 is in the robot coordinates, and control the image acquisition unit 1 to take pictures.

[0086] Furthermore, the present application can also achieve abnormal flame detection.

[0087] As an example, the image acquisition unit 1 is also used to collect the flame image when the blowtorch 2 is working; the image processing unit is also used to process the flame image to obtain the pixel area of the flame region; the control unit is also used to compare the pixel area of the flame region with the pixel area value range. If it is within the pixel area value range, the flame is normal, otherwise, the flame is abnormal.

[0088] In this example, as shown in Figure 6 After image processing, a grayscale image of the flame image can be obtained, and the pixel area of the flame region, that is, the area occupied by the pixel points, can be calculated. For a normal flame, the area occupied by its pixel points can be set to a value range, that is, the pixel area value range. If the pixel area of the identified flame region is within this value range, it indicates that the flame is normal, otherwise, it indicates that the flame is abnormal.

[0089] For abnormal situations, relevant personnel can be reminded in time.

[0090] As another example, a set of flame image samples can be collected first. The set of flame image samples includes multiple color flame samples, and the color flame samples are color images of the normal flame generated when the blowtorch 2 is working, and the normal flame covers the entire area of the color image. By processing each color flame sample through the image processing unit, the R value ratio, G value ratio, and B value ratio in each color flame sample can be obtained. For example, if there are 10,000 pixel points in a color flame sample, the R value, G value, and B value of each pixel point can be obtained. The total value is obtained by summing up the 30,000 values of the R values, G values, and B values of the 10,000 pixel points. The R value ratio is obtained by dividing the sum of the R values of the 10,000 pixel points by the total value. Similarly, the G value ratio and B value ratio are obtained. Therefore, the sum of the R value ratio, G value ratio, and B value ratio is equal to 100%.

[0091] Find the maximum and minimum values of the R value ratio from all the color flame samples to obtain the R value ratio value range. Find the maximum and minimum values of the G value ratio from all the color flame samples to obtain the G value ratio value range. Find the maximum and minimum values of the B value ratio from all the color flame samples to obtain the B value ratio value range.

[0092] The color flame image when the blowtorch 2 is working is collected through the image acquisition unit 1. The image processing unit processes the color flame image, and the R value ratio, G value ratio, and B value ratio in the color flame image can be obtained. The control unit compares the R value ratio, G value ratio, and B value ratio in the color flame image with the R value ratio value range, G value ratio value range, and B value ratio value range respectively. If the R value ratio is within the R value ratio value range, the G value ratio is within the G value ratio value range, and the B value ratio is within the B value ratio value range, the flame is normal; otherwise, the flame is abnormal.

[0093] In the description of the present application, it should be noted that the orientation or positional relationship indicated by terms such as "upper" and "lower" is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present application. Unless otherwise clearly specified and defined, the terms "installation", "connection", and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific situations.

[0094] It should be noted that in this application, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the said element.

[0095] The above are only specific embodiments of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features claimed herein.

Claims

1. A blowtorch detection system, characterized in that: It includes a detection mechanism, which includes: An image acquisition unit (1) is used to face the spray end surface of the blowtorch (2) to acquire an image of the blowtorch hole; An image processing unit connected to the image acquisition unit (1) and used to process the acquired image to obtain quality parameters of each burner hole; A control unit is connected to the image processing unit and compares the pass threshold of the burner hole with the quality parameter of the burner hole to determine whether each burner hole is qualified.

2. The blowtorch detection system according to claim 1, characterized in that: The quality parameter of the burner hole includes the difference between the maximum value and the minimum value of the inner diameter of the burner hole in different directions obtained by processing; When the difference is greater than the pass threshold of the burner hole, the burner hole is deformed and is unqualified.

3. The blowtorch detection system according to claim 1, characterized in that: The quality parameter of the burner hole includes an area ratio, which is the ratio of the area of ​​the burner hole obtained by processing that exceeds the boundary of the standard circular burner hole to the area of ​​the standard circular burner hole when the center of the burner hole obtained by processing coincides with the center of the standard circular burner hole; When the area ratio is greater than the pass threshold of the blowtorch hole, the blowtorch hole is deformed and is unqualified.

4. The blowtorch detection system according to claim 1, characterized in that: The quality parameter of the burner hole includes the gray value of the burner hole obtained by processing. When the gray value is less than the burner hole qualified threshold, there is foreign matter in the burner hole and the burner hole is unqualified. Alternatively, the quality parameter of the blowtorch hole includes the ratio of the dark gray area to the total area of ​​the rectangular area obtained by expanding the blowtorch hole. When the ratio is greater than the qualified threshold of the blowtorch hole, there is foreign matter in the blowtorch hole and it is unqualified.

5. The blowtorch detection system according to claim 1, characterized in that: It also includes: A first base (3) for supporting the blowtorch (2), wherein a light source for irradiating along the axial direction of the blowtorch (2) is arranged on the first base (3); Guide rail (4); A mobile bracket (5) on which the image acquisition unit (1) is mounted; a driving unit (6), connected to the movable support (5) and used to drive the movable support (5) to move on the guide rail (4) so ​​as to approach or move away from the first base (3); The control unit is connected to the drive unit (6) and is used to control the operation of the drive unit (6).

6. The blowtorch detection system according to claim 5, characterized in that: The control unit pre-stores focus positions corresponding to different types of torches (2), the focus position being the position at which the movable bracket (5) moves from the starting point of the guide rail (4) to a position where the torch (2) is at the focus of the image acquisition unit (1); The control unit is also used to receive the type of the blowtorch (2) and drive the movable bracket (5) to move to a corresponding focusing position.

7. The blowtorch detection system according to claim 1, characterized in that: It also includes: AGV (7); A second base (8) mounted on the AGV vehicle (7); A robot (9) mounted on the second base (8), and the image acquisition unit (1) is mounted on an arm of the robot (9); Furthermore, the control unit is also connected to the image acquisition unit (1), the AGV trolley (7) and the robot (9), and is used to control the AGV trolley (7) to move in front of the blowtorch device to be at a preset positioning point, and control the robot (9) to move the image acquisition unit (1) above the blowtorch (2) according to the robot coordinates in the robot coordinate system pre-calibrated by the blowtorch (2) so that the blowtorch (2) is at the robot coordinates, and control the image acquisition unit (1) to shoot, wherein the blowtorch device includes a plurality of blowtorches (2).

8. The blowtorch detection system according to claim 1, characterized in that: It includes: A blowtorch off-line static detection device, comprising: - the detection mechanism; - a first base (3) for supporting the blowtorch (2), wherein a light source for irradiating along the axial direction of the blowtorch (2) is arranged on the first base (3); - guide rail (4); - a mobile support (5) on which the image acquisition unit (1) is mounted; - a driving unit (6), which is connected to the mobile support (5) and is used to drive the mobile support (5) to move on the guide rail (4) to approach or move away from the first base (3); wherein the control unit is connected to the driving unit (6) and is used to control the operation of the driving unit (6); The blowtorch online dynamic detection device comprises: - the detection mechanism; -AGV trolley (7); - a second base (8), which is mounted on the AGV vehicle (7); - a robot (9) mounted on the second base (8), and the image acquisition unit (1) is mounted on the arm of the robot (9); wherein the control unit is also connected to the image acquisition unit (1), the AGV trolley (7) and the robot (9), and is used to control the AGV trolley (7) to move in front of the blowtorch device to be at a preset positioning point, and according to the robot coordinates pre-calibrated by the blowtorch (2) in the robot coordinate system, control the robot (9) to move the image acquisition unit (1) above the blowtorch (2) so that the blowtorch (2) is at the robot coordinates, and control the image acquisition unit (1) to shoot, wherein the blowtorch device comprises a plurality of blowtorches (2).

9. The blowtorch detection system according to claim 1, characterized in that: The image acquisition unit (1) is also used to acquire a flame image of the blowtorch (2) when it is working; The image processing unit is also used to process the flame image to obtain the pixel area of ​​the flame region; The control unit is further used to compare the pixel area of ​​the flame region with a pixel area value range. If the pixel area is within the pixel area value range, the flame is normal; otherwise, the flame is abnormal.

10. The blowtorch detection system according to claim 1, characterized in that: The image acquisition unit (1) is also used to acquire a color flame image of the blowtorch (2) when it is working; The image processing unit is also used to process the collected color flame image to obtain the R value ratio, G value ratio and B value ratio in the color flame image; The control unit is also used to compare the R value proportion, G value proportion and B value proportion in the color flame image with the R value proportion value range, G value proportion value range and B value proportion value range respectively. If they are all within the corresponding value range, the flame is normal, otherwise, the flame is abnormal.

Images