Aviation organic glass and polyester ribbon bonding defect detection system and method

Abstract

The invention belongs to the technical field of aircraft assembly detection, and relates to an aviation organic glass and polyester ribbon bonding defect detection system and method. According to the invention, a digital detection technology is creatively utilized, the system for detecting the bonding quality of the aviation organic glass and the polyester ribbon is designed, a brand new method is provided for detecting the defects of the bonding surface of the glass and the polyester ribbon, and a manual detection mode is thoroughly changed. Through the detection system, collection, transmission and image processing of glass and polyester ribbon bonding surface images, automatic judgment of bonding defects and accurate calculation of the bonding defect area are achieved, finally, a conclusion whether the bonding quality is qualified or not can be automatically judged, and the detection efficiency and accuracy of the glass and polyester ribbon bonding surface defects are remarkably improved.

Description

Technical Field

[0001] The invention belongs to the technical field of aircraft assembly detection, and relates to a system and method for detecting bonding defects of aviation organic glass and polyester ribbon. Background Art

[0002] During the assembly process of an aviation organic glass, it is necessary to use structural adhesive to bond polyester ribbons on both sides of the glass edge. The bonding process is as follows: 1) polish and clean the glass bonding area, and clean the ribbon bonding area; 2) apply structural adhesive to the glass bonding area and the polyester ribbon bonding area; 3) bond the polyester ribbon to the glass, use a special clamp to apply a certain pressure to the bonding surface, and keep it for 24 hours to make the glass and the polyester ribbon fully bonded (pressure loading has an important influence on the bonding quality); 4) remove the special bonding clamp, and cure the bonded parts in a specified environment for a certain period of time; 5) use a prism (a special glass-made detection tool) to perform manual visual inspection of the bonding quality, and the cumulative area of ​​unilateral bonding defects is not allowed to exceed the specified range.

[0003] The current problem is that since defects are generally irregular in shape and relatively scattered, when manually using a prism to detect the bonding quality of glass and polyester ribbon, it is impossible to accurately accumulate and calculate the actual area of ​​each defect on a single side, resulting in low detection accuracy and low efficiency.

[0004] Regarding the testing method for the bonding quality of glass and polyester ribbon, by searching the published patents, the patent number is CN 215701111U, and the patent name is "Adaptive clamp for bonding aviation products". The bonding quality is improved by designing and improving the bonding clamp, but there is no improvement or enhancement on the testing methods and means.

[0005] In view of the above shortcomings in the quality inspection of the bonding between glass and polyester ribbon, it is urgent to invent a detection equipment with simple operation, high visualization, intuitive and accurate test results, shortened test time and improved production efficiency. Summary of the invention

[0006] In view of this, the present invention provides a method and system for rapid intelligent detection of bonding defects between aviation plexiglass and polyester ribbons to solve the above-mentioned problems of low detection efficiency and low accuracy.

[0007] The technical solution of the present invention is as follows:

[0008] A system for detecting defects in the bonding of aviation organic glass and polyester ribbons includes a system startup module, a main control module, a bonding surface image acquisition module, an image processing module, and a defect judgment module. The output end of the system startup module is connected to the input end of the main control module, the output end of the main control module is connected to the input end of the image acquisition module, the output end of the image acquisition module is connected to the input end of the image processing module, and the output end of the image processing module is connected to the defect judgment module. The system block diagram is shown in Figure 1, and the system hardware structure diagram is shown in Figure 2. Figure 2 As shown, the system integration host includes a system startup module, a main control module, an image processing module, and defect judgment module hardware and software.

[0009] The system startup module consists of a power supply and a switch. After the module is working, it can supply power to other modules to ensure the normal operation of the detection system.

[0010] The main control module includes data storage devices, a central processing unit, a display, and a control program, and coordinates and controls the work of other systems.

[0011] The image acquisition module includes a prism made of aviation organic glass, a detection light source, a camera group, and a transmission line. Since the polyester ribbon is folded in half and bonded to both sides of the glass, the camera cannot directly capture the image of the bonding surface, so a prism is added in front of the camera. The prism is specially designed, with one side as the detection surface, one side as the observation surface, and one side as the bottom surface. The shape of the detection surface is coordinated with the shape of the glass surface, and the observation surface and the bottom surface are ∠65°~∠70°. When the detection surface is attached to the glass, the prism is used to produce light refraction, and the bonding surface image can be seen on the observation surface. The schematic diagram of the prism structure is shown below. Figure 3 As shown. The detection light source is installed on the side of the prism to provide illumination for image collection. The camera group is installed on the prism observation surface. When the prism detection surface moves with the glass, the camera group takes a photo and scans the bonding surface to obtain the bonding surface image. At the same time, the collected image is transmitted to the image processing module through the transmission line in real time for analysis and processing.

[0012] The image processing module has the functions of image denoising, edge detection and area calculation. It is used to process the collected bonding surface image, obtain the target area, screen the target area to obtain the suspected abnormal area, perform superpixel segmentation of the suspected abnormal area at different scales, obtain the segmented image of the abnormal area, then mark and number the abnormal image, determine the contour, and calculate the area included in the contour.

[0013] The defect judgment module has the function of identifying and judging bonding defects. Its principle is to use the defect standard type database stored in the computing device to compare the abnormal images screened out in the image processing module, automatically determine whether the abnormal image is a bonding defect, renumber the images determined to be bonding defects and calculate the cumulative area S 累计面积, and then further compare S 累计面积 and S 规定值 , and finally output the conclusion on whether the bonding quality between glass and polyester ribbon is qualified.

[0014] A method for detecting bonding defects between aviation plexiglass and polyester ribbon, the steps are as follows:

[0015] Collect various types of bonding defects, establish a database of standard bonding defect types, and specify the bonding quality standard value S 规定值 ;

[0016] Obtain the image of the bonding surface between glass and polyester ribbon, and identify and determine the defective part by comparing it with the standard types of bonding defects in the database;

[0017] Mark the outline of the bonding defect and mark the defect as A1, A2...A n , the defect contour enclosing area is calculated using the software algorithm, which are S1, S2…S n ,The algorithm is used to calculate the cumulative defect area, and the calculation formula is as follows:

[0018]

[0019] Computer software automatically compares the design standard value S 规定值 For comparison, such as S 累计面积 ≤S 规定值 , then the bonding is qualified, such as S 累计面积 >S 规定值 , the bonding is unqualified.

[0020] Beneficial effects of the present invention:

[0021] The present invention creatively uses digital detection technology to design an aviation organic glass and polyester ribbon bonding quality detection system, which provides a new method for detecting defects on the bonding surface of glass and polyester ribbon, and completely changes the manual detection method. Through the detection system, the acquisition, transmission, image processing, automatic judgment of bonding defects, and accurate calculation of the bonding defect area of ​​the bonding surface of glass and polyester ribbon are realized, and finally the conclusion of whether the bonding quality is qualified can be automatically output, which significantly improves the efficiency and accuracy of the detection of defects on the bonding surface of glass and polyester ribbon. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a block diagram of a glass and polyester ribbon bonding quality inspection system;

[0023] Figure 2 This is a hardware structure diagram of a glass and polyester ribbon bonding quality inspection system;

[0024] Figure 3 Schematic diagram of the prism structure;

[0025] Figure 4 This is the image of block defects in the bonding between glass and polyester ribbon;

[0026] Figure 5 This is an image of a ribbon defect in the bonding between glass and polyester ribbon.

[0027] In the figure: 1 system integration host; 2 prism; 3 camera group; 4 detection light source; 5 data transmission line. DETAILED DESCRIPTION

[0028] Embodiment 1:

[0029] A method for detecting bonding defects between aviation plexiglass and polyester ribbon, the steps are as follows:

[0030] Step 1: Perform a status check on the aviation plexiglass and polyester ribbon bonding defect detection system before use, check the integrity of each part of the system, and confirm the connection integrity of each connection point.

[0031] Step 2: Confirm the status of the workpiece bonded between the aviation plexiglass and the polyester ribbon before inspection, clean and wipe the glass surface with a clean cotton cloth to remove dust and impurities to ensure that the prism and the glass can fit tightly.

[0032] Step 3: Turn on the startup module switch, confirm that the detection system is powered on normally, start the image acquisition module software, turn on the prism protection device, turn on the detection light source, and confirm that the image acquisition module is in working condition and can capture clear photos.

[0033] Step 4: Apply triglyceride on the prism detection surface as a coupling agent between the glass and the prism, and stick the prism detection surface along the edge of the polyester ribbon on the glass surface. Slowly move the prism along the edge of the polyester ribbon to ensure that the camera group collects the bonding surface image stably and continuously. The camera transmits the collected image to the image acquisition module in real time. When the image acquisition is completed, turn off the detection power, clean the glyceride on the prism and glass, and install the prism protection device.

[0034] Step 5: Start the image processing module, retrieve the bonding surface image stored in the image acquisition module, perform noise reduction on the image, screen and obtain the suspected abnormal area, perform superpixel segmentation of the suspected abnormal area at different scales, obtain the segmented image of the abnormal area, calibrate the contour boundary of the area, and then mark and number the calibrated area. The area is generally in block or strip shape.

[0035] Step 6: Start the defect judgment module, call the defect standard type database stored in the memory of the control module, compare the abnormal area of ​​the bonding surface marked in the image processing module, judge whether the abnormal area is a bonding defect, re-mark the part judged as a defect, and mark the outline of the defect, such as Figure 4 , Figure 5 The bonding defect image shown automatically calculates the cumulative defect area S 累计面积 , and with S 规定值 For comparison, such as S 累计面积 ≤S 规定值 , then the bonding is qualified, such as S 累计面积 >S 规定值 , the bonding is unqualified.

[0036] Embodiment 2:

[0037] A system for detecting defects in the bonding of aviation organic glass and polyester ribbons includes a system startup module, a main control module, a bonding surface image acquisition module, an image processing module, and a defect judgment module. The output end of the system startup module is connected to the input end of the main control module, the output end of the main control module is connected to the input end of the image acquisition module, the output end of the image acquisition module is connected to the input end of the image processing module, and the output end of the image processing module is connected to the defect judgment module. The system block diagram is shown in Figure 1, and the system hardware structure diagram is shown in Figure 2. Figure 2 As shown, the system integration host 1 includes a system startup module, a main control module, an image processing module, and defect judgment module hardware and software.

[0038] The system startup module consists of a power supply and a switch. After the module is working, it can supply power to other modules to ensure the normal operation of the detection system.

[0039] The main control module includes data storage devices, a central processing unit, a display, and a control program, and coordinates and controls the work of other systems.

[0040] The image acquisition module includes a prism 2 made of aviation organic glass, a detection light source 4, a camera group 3, and a transmission line. Since the polyester ribbon is folded in half and bonded to both sides of the glass, the camera cannot directly capture the image of the bonding surface, so a prism 2 is added in front of the camera. The prism 2 is specially designed, with one side as the detection surface, one side as the observation surface, and one side as the bottom surface. The shape of the detection surface is coordinated with the shape of the glass surface, and the observation surface and the bottom surface are ∠65°~∠70°. When the detection surface is attached to the glass, the prism 2 generates light refraction, and the bonding surface image can be seen on the observation surface. The schematic diagram of the structure of the prism 2 is shown in the figure. Figure 3As shown. The detection light source 4 is installed on the side of the prism 2 to provide illumination for collecting images. The camera group 3 is installed on the prism observation surface. When the detection surface of the prism 2 moves with the glass, the camera group 3 takes a photo and scans the bonding surface to obtain the bonding surface image, and at the same time transmits the collected image to the image processing module through the transmission line in real time for analysis and processing.

[0041] The image processing module has the functions of image denoising, edge detection and area calculation. It is used to process the collected bonding surface image, obtain the target area, screen the target area to obtain the suspected abnormal area, perform superpixel segmentation of the suspected abnormal area at different scales, obtain the segmented image of the abnormal area, then mark and number the abnormal image, determine the contour, and calculate the area included in the contour.

[0042] The defect judgment module has the function of identifying and judging bonding defects. Its principle is to use the defect standard type database stored in the computing device to compare the abnormal images screened out in the image processing module, automatically determine whether the abnormal image is a bonding defect, renumber the images determined to be bonding defects and calculate the cumulative area S 累计面积 , and then further compare S 累计面积 and S 规定值 , and finally output the conclusion on whether the bonding quality between glass and polyester ribbon is qualified.

Claims

1. A system for detecting bonding defects of aviation plexiglass and polyester ribbon, characterized in that: It includes a system startup module, a main control module, a bonding surface image acquisition module, an image processing module, and a defect judgment module; the output end of the system startup module is connected to the input end of the main control module, the output end of the main control module is connected to the input end of the image acquisition module, the output end of the image acquisition module is connected to the input end of the image processing module, and the output end of the image processing module is connected to the defect judgment module; The image acquisition module comprises a prism (2), a detection light source (4), a camera group (3), and a transmission line; a prism (2) is added in front of the camera, one side of the prism (2) is a detection surface, one side is an observation surface, and one side is a bottom surface, the shape of the detection surface is coordinated with the shape of the glass surface, and the detection light source (4) is installed on the side of the prism (2) to provide illumination when collecting images; the camera group (3) is installed on the prism observation surface, and when the detection surface of the prism (2) moves in contact with the glass, the camera group (3) takes a picture and scans the bonding surface to obtain an image of the bonding surface, and at the same time transmits the collected image to the image processing module through the transmission line in real time for analysis and processing; The image processing module has the functions of image denoising, edge detection and area calculation, and is used to process the collected bonding surface image to obtain the target area, screen the target area to obtain the suspected abnormal area, perform superpixel segmentation of the suspected abnormal area at different scales, obtain the segmented image of the abnormal area, and then mark and number the abnormal image, determine the contour, and calculate the area included in the contour; The defect judgment module has the function of identifying and judging bonding defects. It compares the abnormal images screened out in the image processing module, automatically determines whether the abnormal images are bonding defects, renumbers the images determined to be bonding defects, and calculates the cumulative area S. 累计面积 , and then further compare S 累计面积 and S 规定值 , and finally output the conclusion on whether the bonding quality between glass and polyester ribbon is qualified.

2. The aviation organic glass and polyester ribbon bonding defect detection system according to claim 1, characterized in that: The observation surface and the bottom surface of the prism (2) are at an angle of ∠65° to ∠70°.

3. A system for detecting bonding defects between aviation organic glass and polyester ribbon as claimed in claim 1 or 2, characterized in that: The system startup module includes a power supply and a switch. After the module is working, it can supply power to other modules to ensure the normal operation of the detection system.

4. The aviation organic glass and polyester ribbon bonding defect detection system according to claim 1 or 2, characterized in that: The main control module includes a data storage device, a central processing unit, and a display, and coordinates and controls the work of other systems.

5. The aviation organic glass and polyester ribbon bonding defect detection system as claimed in claim 3, characterized in that: The main control module includes a data storage device, a central processing unit, and a display, and coordinates and controls the work of other systems.

6. The aviation organic glass and polyester ribbon bonding defect detection system as claimed in claim 1, 2 or 5, characterized in that: The prism (2) is made of aviation organic glass.

7. The aviation organic glass and polyester ribbon bonding defect detection system as claimed in claim 3, characterized in that: The prism (2) is made of aviation organic glass.

8. The aviation organic glass and polyester ribbon bonding defect detection system as claimed in claim 4, characterized in that: The prism (2) is made of aviation organic glass.

9. The detection method of the aviation organic glass and polyester ribbon bonding defect detection system according to any one of claims 1 to 8, characterized in that: Here are the steps: Step 1: Collect various types of bonding defects, establish a database of standard bonding defect types, and specify the bonding quality standard value S 规定值 ; Step 2: Obtain an image of the bonding surface between glass and polyester ribbon, and identify and determine the defective part by comparing it with the standard type of bonding defects in the database; Step 3: Mark the outline of the bonding defect and mark the defect as A1, A2...A n , the defect contour enclosing area is calculated using the software algorithm, which are S1, S2…S n ,The algorithm is used to calculate the cumulative defect area, and the calculation formula is as follows: Step 4: Computer software automatically compares the design standard value S 规定值 For comparison, such as S 累计面积 ≤S 规定值 , then the bonding is qualified, such as S 累计面积 >S 规定值 , the bonding is unqualified.

Images