Bonding area detection device based on machine vision

Abstract

The utility model provides a bonding area detection device based on machine vision, and belongs to the technical field of dry-mixed mortar performance testing, the detection device comprises a computer and a detector, the detector comprises a testboard, a CCD camera, a prime lens and a light source; the computer is connected with the CCD camera; vertical rods are arranged on the two sides of the upper portion of the test board respectively, and a first horizontal cross rod and a second horizontal cross rod are arranged between the vertical rods. One end of the camera fixing device is fixed on the first horizontal cross rod, the other end of the camera fixing device is connected with the CCD camera, the CCD camera is connected with the prime lens, the light source fixing device is fixed on the second horizontal cross rod, and a guide rail is arranged on the light source fixing device. According to the dry-mixed mortar tensile adhesive strength measuring device, the ratio r of the effective tensile area to the area of the bonding surface of the drawing joint can be measured, so that errors caused by estimation performed by a visual estimation method by a tester originally are effectively reduced, and the accuracy of measuring the tensile adhesive strength of the dry-mixed mortar is greatly improved.

Description

Technical Field

[0001] The utility model belongs to the technical field of dry-mix mortar performance testing, and in particular relates to a bonding area detection device based on machine vision. Background Art

[0002] Dry-mixed mortar is a dry powder material that is pre-mixed with cement, sand and various additives in a certain proportion. When using it, just add an appropriate amount of water and stir evenly, which is very convenient and quick. It is mainly used in construction such as wall plastering, floor leveling, and tile pasting. Dry-mixed mortar has the advantages of high construction efficiency, stable quality, and reduced on-site dust pollution.

[0003] The determination of the tensile bond strength of dry-mix mortar is of great significance for evaluating its performance. Tensile bond strength is an important indicator to measure the bonding ability between dry-mix mortar and the substrate. This test can help determine whether the mortar can maintain a good bonding state after construction, thereby ensuring the safety and durability of the structure. The test can ensure that the mortar meets the specified standard requirements, which helps manufacturers control product quality; it can help evaluate the performance of the mortar under different environmental conditions, such as temperature changes, humidity changes, etc. At the same time, it provides a basis for construction personnel to help them understand which type of mortar is suitable for specific application scenarios, and helps engineers and architects choose suitable dry-mix mortar products according to the specific needs of the project. The most important thing is to ensure that the mortar will not be damaged when subjected to the expected load, thereby ensuring the stability of the building structure.

[0004] Tensile bond strength is an important performance index of dry-mix mortar. It is usually tested by a pull-out tester to determine its maximum breaking load F, and is expressed by the formula: The tensile bond strength P of the sample is calculated, where S is the tensile area of ​​the sample. In theory, the bonding surface area of ​​the pull-out joint should be taken. However, in the actual test process, due to the different effects of different adhesives and different operating methods, sometimes the adhesive fails to completely bond the pull-out joint to the sample to be tested, so the effective tensile area of ​​the sample will be smaller than the bonding surface area of ​​the pull-out joint. In this case, if the bonding surface area of ​​the pull-out joint is still taken as the effective tensile area S of the sample, 有效 , calculate the bonding strength P 测试 , which will result in the calculated bond strength P 测试 Less than the actual bond strength P of the specimen. The current common correction method is for testers to estimate the ratio r of the effective tensile area to the bonding surface area of ​​the pull-out joint by visual estimation, using the formula: To calculate the tensile bond strength of the sample, and then to correct the calculated value of the bond strength to a certain extent, but due to the lack of more accurate measuring tools, the error of r obtained by this method is very large. Utility Model Content

[0005] In order to overcome the problem that the effective bonding area cannot be accurately measured during the tensile bond strength test in the above-mentioned prior art, the present utility model provides a bonding area detection device based on machine vision, which measures the ratio r of the effective tensile area to the bonding surface area of the pulling joint based on machine vision, thereby improving the accuracy of the tensile bond strength measurement.

[0006] In order to achieve the above object, the technical solution adopted by the present utility model to solve this technical problem is:

[0007] A bonding area detection device based on machine vision, comprising a computer and a detector. The detector includes a test bench, a CCD camera, a fixed-focus lens and a light source; the computer is connected to the CCD camera; on both sides above the test bench, a first vertical rod and a second vertical rod are respectively provided. Between the first vertical rod and the second vertical rod, a first horizontal cross bar and a second horizontal cross bar are provided, and the first horizontal cross bar is above the second horizontal cross bar; one end of the camera fixing device is fixed on the first horizontal cross bar, and the other end is connected to the CCD camera. The CCD camera is connected to the fixed-focus lens; the light source fixing device is fixed on the second horizontal cross bar, and a guide rail is provided on the light source fixing device.

[0008] As a more preferred method, the camera fixing device is fixed on the first horizontal cross bar by a first stepped double-hole single-bolt cross clamp.

[0009] As a more preferred method, four adjustable feet are provided under the test bench for support.

[0010] As a more preferred method, the first vertical rod and the second vertical rod are respectively fixed on both sides of the test bench in the vertical direction by hexagon socket head cap screws.

[0011] As a more preferred method, the first horizontal cross bar and the second horizontal cross bar are respectively fixed to the first vertical rod and the second vertical rod by same-diameter double-hole single-bolt optical axis cross clamps.

[0012] As a more preferred method, the light source fixing device is fixed on the second horizontal cross bar by a second stepped double-hole single-bolt cross clamp.

[0013] As a more preferred method, spirit levels are respectively installed on the test bench and the camera fixing device.

[0014] As a more preferred method, the light source is an annular light source.

[0015] As a more preferred method, both the first horizontal cross bar and the second horizontal cross bar can move up and down along the first vertical rod and the second vertical rod.

[0016] As a more preferred method, the camera fixing device can move left and right along the first horizontal crossbar, the light source fixing device can move left and right along the second horizontal crossbar, and at the same time, the camera fixing device and the light source fixing device can move back and forth.

[0017] The advantages and beneficial effects of the present utility model are as follows:

[0018] 1. The present utility model provides a bond area detection device based on machine vision, which can measure the ratio r of the effective tensile area between the dry-mixed mortar and the pull-out joint to the bond area of the pull-out joint when testing the tensile bond strength of the dry-mixed mortar using a pull-out testing machine. This effectively reduces the error caused by the original method of estimating the ratio of the effective tensile area to the bond area of the pull-out joint by visual estimation by the tester, greatly improving the accuracy of the tensile bond strength measurement, which is of great significance for construction safety.

[0019] 2. By setting a vertical rod, a second vertical rod, a first horizontal crossbar, and a second horizontal crossbar, the camera fixing device can move left and right along the first horizontal crossbar, the light source fixing device can move left and right along the second horizontal crossbar, and at the same time, both the camera fixing device and the light source fixing device can move back and forth along their axes. The guide rail can make the light source move left and right, that is, the device of the present utility model can flexibly adjust the field of view range in the vertical and horizontal directions to adapt to different detection scenarios. Description of the Drawings

[0020] Figure 1 is a schematic structural view of the bond area detection device based on machine vision of the present utility model;

[0021] Figure 2 is a front view structural view of the detector of the bond area detection device based on machine vision of the present utility model;

[0022] Figure 3 is a left view structural view of the detector of the bond area detection device based on machine vision of the present utility model;

[0023] Figure 4 is a top view structural view of the detector of the bond area detection device based on machine vision of the present utility model.

[0024] In the figure, 1. computer, 2. test bench, 3. adjustable support feet, 4. vertical rod, 5. hex socket screw, 6. first horizontal cross bar, 7. second horizontal cross bar, 8. same-diameter double-hole single-bolt optical axis cross clamp, 9. camera fixing device, 10. first different-diameter double-hole single-bolt cross clamp, 11. first hand-tightening screw, 12. CCD camera, 13. fixed-focus lens, 14. light source fixing device, 15. second different-diameter double-hole single-bolt cross clamp, 16. second hand-tightening screw, 17. ring light source, 18. guide rail, 19. first level gauge, 20. second level gauge, 21. first vertical rod, 22. second vertical rod. Detailed implementation manners

[0025] The following will further describe in detail the specific implementation manners of the present utility model with reference to the accompanying drawings. The following embodiments are used to illustrate the present utility model, but are not used to limit the scope of the present utility model.

[0026] Please refer to Figures 1 to 4 , this embodiment provides a bonding area detection device based on machine vision, including a computer 1 and a detector. The detector includes a test bench 2, a ring light source 17 and a CCD camera 12; the computer 1 is connected to the CCD camera 12 through a network cable.

[0027] The CCD camera 12 refers to a digital camera with a charge-coupled device image sensor.

[0028] Four adjustable support feet 3 are provided below the test bench 2. On both sides above the test bench 2, a first vertical rod 21 and a second vertical rod 22 are respectively provided. A horizontally arranged first horizontal cross bar 6 and a second horizontal cross bar 7 are connected between the first vertical rod 21 and the second vertical rod 22. The first horizontal cross bar 6 is above the second horizontal cross bar 7. The first vertical rod 21 and the second vertical rod 22 are respectively fixed on both sides of the test bench 2 in the vertical direction through hex socket screws 5. The first horizontal cross bar 6 and the second horizontal cross bar 7 are respectively fixed to the first vertical rod 21 and the second vertical rod 22 through same-diameter double-hole single-bolt optical axis cross clamps 8.

[0029] The camera fixing device 9 is fixed on the first horizontal crossbar 6 through the first double-hole single-bolt cross clamp 10. By adjusting the fastener on the first double-hole single-bolt cross clamp 10, the front-back movement of the camera fixing device 9 can be achieved. The other end of the camera fixing device 9 is connected to the CCD camera 12. By adjusting the first hand-tightening screw 11 on the camera fixing device 9, the position of the CCD camera 12 can be fixed and adjusted within a certain range. The CCD camera 12 is connected to the fixed-focus lens 13. The light source fixing device 14 is fixed on the second horizontal crossbar 7 through the second double-hole single-bolt cross clamp 15. By adjusting the fastener on the second double-hole single-bolt cross clamp 15, the front-back movement of the light source fixing device 14 can be achieved. At the same time, a guide rail 18 is provided on the light source fixing device 14. By adjusting the second hand-tightening screw 16 on the light source fixing device 14, the position of the annular light source 17 can be fixed. If the second hand-tightening screw 16 is loosened and the guide rail 18 is used at the same time, the left-right position of the annular light source 17 can be adjusted within a certain range. After the adjustment is completed, the second hand-tightening screw 16 can be fixed again.

[0030] Data is transmitted between the computer 1 and the CCD camera 12 in a wired manner through a network cable. The computer end is an RJ45 interface, and the CCD camera 12 end is a GigE interface, both of which are gigabit network ports. The CCD camera 12 acquires the RGB image of the bonding surface of the pulled joint after pulling and transmits it to the computer in real time through the network cable.

[0031] A second level 20 is installed on the test bench 2. A first level 19 is installed on the camera fixing device 9.

[0032] The annular light source 17 is connected to the light source controller, and the intensity of the light source can be adjusted by adjusting the light source controller.

[0033] Both the first horizontal crossbar 6 and the second horizontal crossbar 7 can move up and down along the first vertical rod 21 and the second vertical rod 22. The camera fixing device 9 can move left and right along the first horizontal crossbar 6. The light source fixing device 14 can move left and right along the second horizontal crossbar 7. At the same time, both the camera fixing device 9 and the light source fixing device 14 can move back and forth along their axes, that is, the field of view can be flexibly adjusted in the vertical and horizontal directions to adapt to different detection scenarios.

[0034] The detector is mainly used to acquire the RGB image of the bonding surface of the pulled joint after pulling. Image processing software is installed on the computer. The image processing software on the computer processes the RGB image acquired by the detector to obtain the effective tensile area, which is specifically realized by the following steps.

[0035] S1: Perform grayscale processing on the acquired RGB image based on the weighted average method. The formula is as follows:

[0036] Gray(i,j) = 0.299 * R (i,j) + 0.578 * G (i,j) + 0.114 * B (i,j) ;

[0037] Where Gray (i,j) is the grayscale value; R (i,j) , G (i,j) , B (i,j) respectively represent the red, green, and blue components at position (i,j).

[0038] S2: Apply Gaussian filtering to the obtained grayscale image for noise reduction; Gaussian filtering is to convolve the image with a Gaussian kernel generated by the Gaussian function to suppress Gaussian noise.

[0039] S3: Based on the canny operator, perform image edge segmentation on the grayscale image after Gaussian filtering, divide the image into a background area, a valid bonding area, and an invalid bonding area, and calculate the ratio r of the area of the valid bonding area to the bonding surface area of the pull-out joint.

[0040] S4: Combine the area S of the bonding surface of the pull-out joint input by the tester to calculate the effective bonding area of the tested pull-out joint.

[0041] During the test, turn on the image processing software on computer 1, automatically connect to CCD camera 12 and display the actual field of view in the image display area of the software through wired transmission. Place the pull-out joint to be tested in the central area of the field of view of CCD camera 12 with the help of the real-time image, adjust the focal length of CCD camera 12 and the light source intensity, and take a picture when a clear image appears. The software automatically processes the taken image based on machine vision, identifies the background area composed of test bench 2, the valid bonding area of the pull-out joint, and the invalid bonding area of the pull-out joint, and gives the ratio r of the valid bonding area of the pull-out joint to the total area of the pull-out joint.

[0042] The above is only a preferred embodiment of the present invention, and does not impose any form of limitation on the present invention; any ordinary technician in the industry can smoothly implement the present invention as shown in the accompanying drawings of the specification and the above description; however, any equivalent changes made by those skilled in the art within the scope of the technical solution of the present invention by using the technical content disclosed above, such as minor modifications, decorations, and evolutions, are equivalent embodiments of the present invention; at the same time, any equivalent changes, modifications, and evolutions made to the above embodiments based on the essential technology of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A bonding area detection device based on machine vision, characterized in that: The invention comprises a computer and a detector, wherein the detector comprises a test bench, a CCD camera, a fixed-focus lens and a light source; the computer is connected to the CCD camera; a first vertical bar and a second vertical bar are respectively arranged on both sides above the test bench, a first horizontal cross bar and a second horizontal cross bar are arranged between the first vertical bar and the second vertical bar, and the first horizontal cross bar is above the second horizontal cross bar; one end of a camera fixing device is fixed on the first horizontal cross bar, and the other end is connected to the CCD camera, and the CCD camera is connected to the fixed-focus lens; a light source fixing device is fixed on the second horizontal cross bar, and a guide rail is arranged on the light source fixing device.

2. The bonding area detection device based on machine vision according to claim 1, characterized in that: The camera fixing device is fixed on the first horizontal cross bar through a first different-diameter double-hole single-bolt cross clamp.

3. The bonding area detection device based on machine vision according to claim 1, characterized in that: Four adjustable feet are provided under the test bench.

4. The bonding area detection device based on machine vision according to claim 1, characterized in that: The first vertical rod and the second vertical rod are respectively fixed on two sides of the test bench along the vertical direction by hexagon socket screws.

5. The bonding area detection device based on machine vision according to claim 4, characterized in that: The first horizontal cross bar and the second horizontal cross bar are respectively fixed to the first vertical bar and the second vertical bar through a same-diameter double-hole single-bolt optical axis cross clamp.

6. The bonding area detection device based on machine vision according to claim 1, characterized in that: The light source fixing device is fixed on the second horizontal cross bar through a second different-diameter double-hole single-bolt cross clamp.

7. The bonding area detection device based on machine vision according to claim 1, characterized in that: Level meters are installed on the test bench and the camera fixing device respectively.

8. The bonding area detection device based on machine vision according to claim 1, characterized in that: The light source is a ring-shaped light source.

9. The bonding area detection device based on machine vision according to claim 1, characterized in that: The first horizontal cross bar and the second horizontal cross bar can both move up and down along the first vertical bar and the second vertical bar.

10. The bonding area detection device based on machine vision according to claim 1, characterized in that: The camera fixing device can move left and right along the first horizontal cross bar, and the light source fixing device can move left and right along the second horizontal cross bar. At the same time, the camera fixing device and the light source fixing device can move forward and backward.

Images