Noodle packaging bag damage detection device based on visual detection

Abstract

The invention discloses a noodle packaging bag damage detection device based on visual detection, and relates to the technical field of damage detection devices. Through cooperation of an electric telescopic rod, a lifting plate, a movable rod fixing screw rod, an extrusion block and a limiting block, the height of the detector is convenient to adjust, and the mounting stability and the positioning accuracy of the detector are improved; through positioning and splicing of a multi-frame image structure gray block based on a damage detection module, complete contours of packaging bags in different sizes and different placement postures can be dynamically reconstructed, contour extraction failure caused by deviation, deformation or shielding of the packaging bags is avoided, and the application range and accuracy of detection are improved; a double comparison mechanism of a structural gray block and a standard gray value is adopted, local gray features are further analyzed on the basis of judging contour integrity, various damage types such as tiny pinholes, local cracks and uneven sealing are effectively recognized, and the defect detection rate and recognition precision are greatly improved.

Description

Technical Field

[0001] This invention relates to the field of damage detection devices, and more particularly to a damage detection device for noodle packaging bags based on vision detection. Background Technology

[0002] As a staple food for the general public, the integrity of the packaging of noodles directly determines the product's shelf life, food safety, and consumer experience. Noodle packaging bags are mostly made of plastic or composite film materials, which are prone to damage such as pinholes, cracks, and poor sealing during production, packaging, and transportation. If damaged products enter the market, the noodles will become damp, clump together, and become contaminated and spoiled, causing food safety hazards. At the same time, it will damage the company's brand reputation and result in losses from mass recalls. Existing noodle packaging bag damage detection devices typically use fixed-distance supplementary lights, resulting in limited light coverage. Furthermore, during the supplementary lighting process, the packaging bag surface is prone to reflections and shadows, leading to insufficient contrast between the damaged and normal areas. This makes it difficult for the algorithm to identify the damaged area. In addition, the detector installation is unstable, and the detector height cannot be effectively adjusted during detection, thus limiting the detection to the same type of noodle packaging. Therefore, the above-mentioned technical problems need to be addressed. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of the existing technology and propose a visual inspection-based noodle packaging bag damage detection device.

[0004] To achieve the above objectives, the present invention adopts the following technical solution: a noodle packaging bag damage detection device based on visual inspection, comprising a support frame, symmetrically installed upper protective plates and uprights symmetrically fixed to one side of the protective plates, a moving mechanism for uniformly moving the noodle packaging bag to the detection area is installed between the protective plates, a sliding frame is fixed to the upper end of the uprights by a positioning mechanism, a support plate is horizontally fixed to the top of the sliding frame, and a lifting mechanism for adjusting the height of the detection device is installed on the support plate; A controller is installed on the support frame, and the controller has a damage detection module inside. The damage detection module converts and divides the images acquired by the detection device into grayscale values. Based on the grayscale mean and standard deviation, it detects abnormal grayscale values ​​in each block and selects the highest quality image by the number of abnormal blocks. It locates structural blocks by combining the grayscale features of the standard packaging bag and stitches together multiple frames of images to obtain the complete outline of the packaging bag. It compares the standard outline with the grayscale values, and if the proportion of abnormal structural blocks exceeds the standard, it is determined to be damaged.

[0005] Preferably, the data analysis steps of the damage detection module are as follows: M1: After the final analysis image is determined, the local outline of the packaging bag is drawn according to the position of the structural gray block in each final analysis image, based on the image acquisition time sequence, and then spliced ​​into a complete outline in sequence; the complete outline is compared with the preset standard outline by inflection point alignment and overlap. If the outlines overlap, the packaging bag outline is determined to be complete; otherwise, it is determined to be incomplete. M2: Under the premise of complete outline, extract the measured gray values ​​of each structural gray block within the outline of the packaging bag and compare them with the gray standard values ​​of the corresponding positions of the standard packaging bag; if the measured value of a structural gray block exceeds the standard fluctuation range, it is marked as an abnormal structural block; if the number of abnormal structural blocks exceeds the preset proportion of the total number of structural gray blocks within the outline, it is determined that the noodle packaging bag is damaged.

[0006] Preferably, the moving mechanism includes rollers symmetrically rotatably mounted at both ends between the guard plates, a conveyor belt is fitted on the rollers, and a servo motor is mounted on the guard plate at one end of one of the rollers, with the output end of the servo motor passing through the guard plate and coaxially fixed to one end of the roller.

[0007] Preferably, the positioning mechanism includes square positioning holes vertically and equidistantly opened on one side of the upright, a positioning rod inserted into the positioning hole, a positioning opening at one end of the positioning rod located inside the positioning hole, a locking block symmetrically hinged in the positioning opening, a connecting rod hinged between the locking blocks, the other end of the connecting rod hinged to a pull rod movably installed in the positioning rod, a sliding frame fixed in the positioning holes symmetrically inserted into the positioning rod on both sides, and a telescopic spring installed inside the positioning rod, a moving plate installed between the telescopic spring and the locking block.

[0008] Preferably, the lifting mechanism includes an electric telescopic rod installed on the upper end of the support plate. The telescopic end of the electric telescopic rod passes through the support plate and is fixed to the upper end of the lifting plate. One end of the lifting plate is movably and slidably installed in the T-shaped groove vertically opened by the moving rod through a T-shaped block, and a visual detector is fixedly connected to one end of the lifting plate.

[0009] Preferably, sliding rods are symmetrically slidably mounted on the sliding frame, supplementary lights are mounted opposite each other on the sliding rods, and the bottom of the sliding rods is fixed to the sliding frame by positioning screws.

[0010] Preferably, one end of the movable rod has an internally threaded hole through it between the sliding frames, and a fixing screw is threaded into the internally threaded hole. Limiting blocks are symmetrically installed between the sliding frames inside the movable rod, and a pressing block is installed between the limiting blocks. One end of the pressing block abuts against one end of the fixing screw.

[0011] Preferably, a positioning plate is installed opposite to the upper end of the conveyor belt, a positioning rod is rotatably installed at one end of the positioning plate, the positioning rod is installed on the fixed plate by a threaded connection, the fixed plate is fixedly connected with threaded sleeves at equal intervals, and the fixed plate is fixedly connected to the outer wall of the guard plate.

[0012] Compared with the prior art, the beneficial effects of the present invention are: 1. By using the sliding rod, supplementary light, and positioning screw, surface reflection and shadows are avoided, improving the adaptability of supplementary lighting and the clarity of image acquisition, thus enabling precise supplementary lighting. Furthermore, by using the electric telescopic rod, lifting plate, moving rod fixing screw, squeezing block, and limiting block, the detector height can be easily adjusted, improving the stability and positioning accuracy of the detector installation, thus enabling the detector height adjustment function. Ultimately, this solves the problems of difficult identification and difficult adjustment of detection height. 2. By using the damage detection module to locate and stitch together structural grayscale blocks from multiple frames of images, the complete outline of packaging bags of different sizes and orientations can be dynamically reconstructed. This avoids outline extraction failures caused by packaging bag offset, deformation, or occlusion, thus improving the applicability and accuracy of the detection. The dual comparison mechanism of structural grayscale blocks and standard grayscale values ​​is adopted to further analyze local grayscale features based on the judgment of outline integrity. This can effectively identify various damage types such as pinholes, local cracks, and uneven sealing, significantly improving the defect detection rate and recognition accuracy. Attached Figure Description

[0013] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings: Figure 1 This is a schematic diagram of the overall three-dimensional structure proposed in this invention; Figure 2 This is a schematic diagram of the overall three-dimensional structure of the other side proposed in this invention; Figure 3 This is a schematic diagram of the overall three-dimensional structure proposed in this invention from a bottom-view perspective; Figure 4 This is a schematic diagram of the three-dimensional structure of the positioning rod proposed in this invention; Figure 5 This is a cross-sectional three-dimensional structural diagram of the positioning rod proposed in this invention; Figure 6 This is a schematic diagram of the side cross-sectional structure proposed in this invention; Figure 7 The present invention proposes Figure 6 Enlarged schematic diagram of the structure at part A in the middle; Figure 8 This is a flowchart of the system proposed in this invention.

[0014] The components in the diagram are numbered as follows: 1. Support frame; 2. Conveyor belt; 3. Positioning plate; 4. Fixing plate; 5. Positioning rod; 6. Upright pole; 7. Sliding frame; 8. Moving rod; 9. Support plate; 10. Electric telescopic rod; 11. Lifting plate; 12. Sliding rod; 13. Supplementary light; 14. Vision detector; 15. Positioning hole; 16. Servo motor; 17. Positioning screw; 18. Positioning insert rod; 19. Pull rod; 21. Snap-fit ​​block; 22. Connecting rod; 23. Telescopic spring; 24. Moving plate; 25. Fixing screw; 26. Limiting block; 27. Extrusion block. Detailed Implementation

[0015] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0016] Example 1: See Figures 1 to 7The present invention discloses a visual inspection-based noodle packaging bag damage detection device, comprising a support frame 1, symmetrically installed upper protective plates on the support frame 1, and uprights 6 symmetrically fixed to one side of the protective plates. A moving mechanism for uniformly moving the noodle packaging bag to the detection area is installed between the protective plates. A sliding frame 7 is fixed to the upper end of the uprights 6 via a positioning mechanism. A support plate 9 is horizontally fixed to the top of the sliding frame 7. A lifting mechanism for adjusting the height of the detection device is installed on the support plate 9. The device is constructed using the support frame 1, protective plates, uprights 6, moving mechanism, positioning mechanism, and sliding frame 7. The moving frame 7, support plate 9, and lifting mechanism facilitate the construction of the overall framework for a vision-based noodle packaging bag damage detection device. They integrate functions such as uniform bag conveying, detection component positioning, and height adjustment, providing a core structural foundation for damage detection. The moving mechanism includes rollers symmetrically rotated at both ends between the guard plates. A conveyor belt 2 is fitted onto the rollers, and a servo motor 16 is mounted on the guard plate at one end of one of the rollers. The output end of the servo motor 16 passes through the guard plate and is coaxially fixed to one end of the roller. The device operates via the rollers, conveyor belt 2, and servo motor 16. The guard plate facilitates the uniform speed operation of the conveyor belt 2, driving the noodle packaging bag to move stably to the inspection area, ensuring the continuity of visual inspection and the consistency of the inspection position; the positioning mechanism includes square positioning holes 15 vertically and equidistantly opened on one side of the upright 6, into which positioning rods 18 are inserted. One end of the positioning rod 18 is located inside the positioning hole 15 and has a positioning opening. A locking block 21 is symmetrically hinged in the positioning opening, and a connecting rod 22 is hinged between the locking blocks 21. The other end of the connecting rod 22 is hinged to a component movably installed in the positioning rod 18. At one end of the pull rod 19, the positioning rod 18 is symmetrically inserted into the positioning holes 15 on both sides to fix the sliding frame 7. The positioning rod 18 is equipped with a telescopic spring 23. A moving plate 24 is installed between the telescopic spring 23 and the snap-fit ​​block 21. Through the upright 6, positioning holes 15, positioning rod 18, snap-fit ​​block 21, connecting rod 22, pull rod 19, sliding frame 7, telescopic spring 23, and moving plate 24, it is easy to realize the rapid positioning and fixation of the sliding frame 7 on the upright 6, adapt to the detection requirements of different heights, and ensure the stability of the installation of the detection components.

[0017] In this invention, the lifting mechanism includes an electric telescopic rod 10 installed on the upper end of a support plate 9. The telescopic end of the electric telescopic rod 10 passes through the support plate 9 and is fixed to the upper end of a lifting plate 11. One end of the lifting plate 11 is movably and slidably installed in a vertically opened T-shaped groove of a moving rod 8 via a T-shaped block. A vision detector 14 is fixedly connected to one end of the lifting plate 11. Through the support plate 9, the electric telescopic rod 10, the lifting plate 11, the moving rod 8, and the vision detector 14, the height of the vision detector 14 can be precisely adjusted to adapt to the detection needs of different specifications of noodle packaging bags and improve the accuracy of damage detection. Sliding rods 12 are symmetrically slidably installed on the sliding frame 7. Supplementary lights 13 are installed opposite to each other on the sliding rods 12. The bottom of the sliding rods 12 is fixed to the sliding frame 7 by a positioning screw 17. Through the sliding frame 7, the sliding rods 12, the supplementary lights 13, and the positioning screw 17, the position of the supplementary lights 13 can be easily adjusted to provide uniform supplementary lighting to the detection area, improve the imaging clarity of the vision detector 14, and ensure the accuracy of packaging bag damage detection. One end of the moving rod 8 is provided with an internal threaded hole between the sliding frames 7, and a fixing screw 25 is threadedly connected to the internal threaded hole. Limiting blocks 26 are symmetrically installed between the sliding frames 7 inside the moving rod 8. An extrusion block 27 is installed between the limiting blocks 26. One end of the extrusion block 27 abuts against one end of the fixing screw 25. The moving rod 8, fixing screw 25, limiting blocks 26, extrusion blocks 27, and sliding frames 7 are used to fix the position of the moving rod 8, ensure the structural stability of the lifting mechanism during operation, and avoid the visual detector 14 from shifting and affecting the damage detection results. A positioning plate 3 is installed opposite to the upper end of the conveyor belt 2. A positioning rod 5 is rotatably installed on one end of the positioning plate 3. The positioning rod 5 is threadedly connected to the fixing plate 4. Threaded sleeves are fixed to the fixing plate 4 at equal intervals. The fixing plate 4 is fixed to the outer wall of the guard plate. The conveyor belt 2, positioning plate 3, positioning rod 5, fixing plate 4, threaded sleeves, and guard plate are used to limit and guide the noodle packaging bags on the conveyor belt 2, prevent the packaging bags from shifting during transportation, and ensure the alignment accuracy of the detection area.

[0018] Working principle: When using this invention, the debugging and calibration of each structure must be completed first to adapt to the testing requirements. The specific process is as follows: First, according to the height specifications of the noodle packaging bag to be tested, move the sliding frame 7 up and down to a suitable position so that the vision detector 14 installed on the lifting plate 11 is initially aligned with the detection area of ​​the conveyor belt 2 above the support frame 1. Then, insert the positioning rod 18 symmetrically into the positioning holes 15 corresponding to the two uprights 6, press the pull rod 19 inside the positioning rod 18, and drive the symmetrical locking block 21 inside the positioning port to open from the positioning port and press against the inner wall of the positioning hole 15 through the connecting rod 22. At the same time, the telescopic spring 23 inside the positioning rod 18 pushes the moving plate 24 to press against the locking block 21, so that the locking block 21 is kept in the open and locked state, thereby realizing the stable fixation of the sliding frame 7 on the uprights 6. If a fine adjustment of the position is required, pull the pull rod 19 in the opposite direction to unlock the locking block 21. Next, rotate the fixing screw 25 at one end of the moving rod 8. The fixing screw 25 is pushed in through the internal threaded hole on the moving rod 8, squeezing the squeezing block 27 located between the limiting blocks 26 inside the moving rod 8. The limiting block 26 locks the position of the moving rod 8 on the sliding frame 7, ensuring that the vision detector 14 is accurately aligned laterally with the center area of ​​the conveyor belt 2. Then, slide the symmetrical sliding rod 12 on the sliding frame 7 to adjust the spacing of the supplementary lights 13 on both sides, so that the supplementary lights 13 are symmetrically distributed on both sides of the detection area to provide a uniform light source. Then, lock and fix the sliding rod 12 on the sliding frame 7 through the positioning screw 17 at the bottom of the sliding rod 12. At the same time, according to the width of the noodle packaging bag to be detected, rotate the positioning rod 5 on the fixing plate 4 to drive the positioning plate 3 at the upper end of the conveyor belt 2 to move laterally to a suitable position. The fixing plate 4 is fixed to the outer wall of the guard plate at equal intervals through the threaded sleeve, which can ensure the stability of the positioning plate 3 after adjustment and realize the limiting guidance of the packaging bag conveying process. After debugging, the electric telescopic rod 10 on the upper end of the support plate 9 is activated. The telescopic end of the electric telescopic rod 10 passes through the support plate 9, driving the lifting plate 11 to move up and down. One end of the lifting plate 11 slides in the T-slot of the moving rod 8 through a T-block to ensure smooth lifting and lowering, thereby accurately adjusting the height of the vision detector 14 to adapt to the detection needs of noodle packaging bags of different thicknesses and improve the accuracy of damage detection. Then, the supplementary light 13 is turned on and adjusted to a suitable brightness to avoid excessive light causing reflection or insufficient light causing blurry imaging. At the same time, the vision detector 14 is activated to take pictures and calibrate standard undamaged noodle packaging bags and set the damage recognition parameters. Finally, the servo motor 16 installed on the guard plate is activated. The output end of the servo motor 16 passes through the guard plate and is coaxially fixed to one of the rollers, driving the roller to drive the conveyor belt 2 to rotate at a uniform speed. The operator neatly places the noodle packaging bags at the input end of the conveyor belt 2. Under the guidance of the positioning plate 3, the packaging bags move stably along the conveyor belt 2 and enter the detection area in sequence. The vision detector 14 continuously detects the noodle packaging bags during the movement to complete the damage detection work.

[0019] Example 2: See Figure 8 A controller is installed on the support frame 1, and the controller has a damage detection module inside; The damage detection module converts and divides the images acquired by the detection device into grayscale values. Based on the grayscale mean and standard deviation, it detects abnormal grayscale values ​​in each block and selects the highest quality image by the number of abnormal blocks. It then locates structural blocks by combining the grayscale features of the standard packaging bag and stitches together multiple frames to obtain the complete outline of the packaging bag. By comparing the standard outline with the grayscale values, if the proportion of abnormal structural blocks exceeds the standard, the bag is determined to be damaged. The height setting module acquires the length, width, and height data of the packaging bag and calculates the height of the supplementary light using empirical formulas; based on the imaging principle and the sensor size, lens focal length, and required field of view of the selected camera, it calculates the installation height of the vision detector. The real-time acquired image data is processed into grayscale, and the grayscale image is segmented according to the size of pixel blocks, resulting in... The image data consists of several identical grayscale blocks, numbered according to their row and column numbers on the grayscale image. The acquired image data is sorted by acquisition time, and the corresponding numbered grayscale blocks within a single image acquired at the same time are further analyzed. Average the gray values and standard deviation The calculation, and the mean obtained from the calculation. and standard deviation Range of grayscale data The setting compares the corresponding grayscale value data with the corresponding grayscale value fluctuation range, marks the corresponding grayscale value data that is outside the fluctuation range as an outlier, and records the number of outliers. ; like If the grayscale data is abnormal, the grayscale data will be detected again. This is a preset proportional coefficient; if If outliers are removed, the remaining grayscale data after outlier removal is averaged. The calculation, and the mean obtained from the calculation. As the grayscale value data detected at the corresponding time; If the grayscale data is still determined to be abnormal upon re-inspection, then the corresponding numbered grayscale block is determined to be abnormal; after determining the grayscale values ​​of all numbered grayscale blocks on the grayscale image, the number of abnormal grayscale blocks is calculated. Record and take the quantity The smallest grayscale image is used as the preliminary analysis image. Based on the standard grayscale values ​​of the noodle packaging bag, the grayscale values ​​of all grayscale blocks in the preliminary analysis image are compared to determine the corresponding grayscale block number for the noodle packaging bag. These grayscale blocks are named structural grayscale blocks. The number of grayscale block anomalies in the structural grayscale blocks of the preliminary analysis image is then analyzed. Perform statistics and collect quantities. The image with the smallest grayscale value is the final image for analysis; The acquired image data is arranged sequentially according to the order in which it is acquired during the movement process. The final analysis image corresponding to each sequence is then determined. Based on the position of the corresponding structural grayscale block on the final analysis image, the outline of the noodle packaging bag is drawn. Then, the entire outline of the noodle packaging bag is spliced ​​together according to the final analysis image corresponding to the arrangement order. The complete outline of the noodle packaging bag is recorded. The corner points of the real-time recorded outline and the preset standard noodle packaging bag outline are marked and compared for overlap. If the outline lines also overlap, the noodle packaging bag outline is determined to be complete; otherwise, the noodle packaging bag outline is determined to be incomplete.

[0020] The corresponding structural grayscale block numbers within the outline of the noodle packaging bag are obtained, and the grayscale value (measured grayscale value) of the corresponding numbered structural grayscale block is compared with the grayscale value (standard grayscale value) of the corresponding numbered structural grayscale block of the standard part. If the measured grayscale value is within the fluctuation range of the standard grayscale value, the structural grayscale block with that number is determined to be normal; otherwise, the abnormal structural grayscale block is marked as abnormal. If the number of structural grayscale blocks with abnormal markings exceeds a preset proportion of the total number of structural grayscale blocks within the outline of the noodle packaging bag, the noodle packaging bag is determined to be abnormal.

[0021] To ensure the light covers the entire bag, the height of the supplementary light needs to be met. , Let this be the maximum diagonal length of the bag on the illuminated plane. This refers to the partial illumination angle of the light source; to avoid the light being too perpendicular and causing reflections to directly enter the camera, the height of the fill light should be adjusted. Adjusted to: , This is the horizontal coverage factor. For the height compensation coefficient, , , These represent the length, width, and height of the noodle packaging bag, respectively; (coefficients were obtained through experimental fitting). Based on the imaging formula: , The horizontal dimension of the field of view. The sensor size is in the horizontal direction. Given the focal length, calculate the corresponding height of the vision detector 14. ; Before conducting damage detection, the height of the supplementary light and the height of the vision detector are pre-adjusted based on the parameter data of the noodle packaging bag.

[0022] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A visual inspection-based noodle packaging bag damage detection device, comprising a support frame (1), a protective plate symmetrically installed on the upper end of the support frame (1), and uprights (6) symmetrically fixed to one side of the protective plate, characterized in that: A moving mechanism for moving the noodle packaging bag to the detection area at a constant speed is installed between the guard plates. A sliding frame (7) is fixed to the upper end of the upright (6) by a positioning mechanism. A support plate (9) is horizontally fixed to the top of the sliding frame (7). A lifting mechanism for adjusting the height of the detection device is installed on the support plate (9). A controller is installed on the support frame (1), and a damage detection module is installed inside the controller; The damage detection module converts and divides the images acquired by the detection device into grayscale values. Based on the grayscale mean and standard deviation, it detects abnormal grayscale values ​​in each block and selects the highest quality image by the number of abnormal blocks. It locates structural blocks by combining the grayscale features of the standard packaging bag and stitches together multiple frames of images to obtain the complete outline of the packaging bag. It compares the standard outline with the grayscale values, and if the proportion of abnormal structural blocks exceeds the standard, it is determined to be damaged.

2. The noodle packaging bag damage detection device based on vision detection according to claim 1, characterized in that: The data analysis steps of the damage detection module are as follows: M1: After the final analysis image is determined, the local outline of the packaging bag is drawn according to the position of the structural gray block in each final analysis image, based on the image acquisition time sequence, and then spliced ​​into a complete outline in sequence; the complete outline is compared with the preset standard outline by inflection point alignment and overlap. If the outlines overlap, the packaging bag outline is determined to be complete; otherwise, it is determined to be incomplete. M2: Under the premise of complete outline, extract the measured gray values ​​of each structural gray block within the outline of the packaging bag and compare them with the gray standard values ​​of the corresponding positions of the standard packaging bag; if the measured value of a structural gray block exceeds the standard fluctuation range, it is marked as an abnormal structural block; if the number of abnormal structural blocks exceeds the preset proportion of the total number of structural gray blocks within the outline, it is determined that the noodle packaging bag is damaged.

3. The noodle packaging bag damage detection device based on vision detection according to claim 1, characterized in that: The moving mechanism includes rollers symmetrically rotated and installed at both ends between the guard plates. A conveyor belt (2) is fitted on the rollers, and a servo motor (16) is installed on the guard plate at one end of one of the rollers. The output end of the servo motor (16) passes through the guard plate and is coaxially fixed to one end of the roller.

4. The noodle packaging bag damage detection device based on vision detection according to claim 3, characterized in that: The positioning mechanism includes square positioning holes (15) vertically and equidistantly opened on one side of the upright (6). A positioning rod (18) is inserted into the positioning hole (15). One end of the positioning rod (18) is located inside the positioning hole (15) and has a positioning opening. A locking block (21) is symmetrically hinged in the positioning opening. A connecting rod (22) is hinged between the locking blocks (21). The other end of the connecting rod (22) is hinged to one end of a pull rod (19) movably installed in the positioning rod (18). A sliding frame (7) is fixed in the positioning holes (15) on both sides of the positioning rod (18). A telescopic spring (23) is installed inside the positioning rod (18). A moving plate (24) is installed between the telescopic spring (23) and the locking block (21).

5. The noodle packaging bag damage detection device based on vision detection according to claim 1, characterized in that: The lifting mechanism includes an electric telescopic rod (10) installed on the upper end of the support plate (9). The telescopic end of the electric telescopic rod (10) passes through the support plate (9) and is fixed to the upper end of the lifting plate (11). One end of the lifting plate (11) is movably and slidably installed in the T-shaped groove vertically opened by the moving rod (8) through a T-shaped block, and a visual detector (14) is fixed to one end of the lifting plate (11).

6. The noodle packaging bag damage detection device based on vision detection according to claim 4, characterized in that: Sliding rods (12) are symmetrically slidably mounted on the sliding frame (7). Fill lights (13) are installed opposite each other on the sliding rods (12), and the bottom of the sliding rods (12) is fixed to the sliding frame (7) by positioning screws (17).

7. The noodle packaging bag damage detection device based on vision detection according to claim 5, characterized in that: One end of the moving rod (8) is provided with an internal threaded hole between the sliding frames (7), and a fixing screw (25) is threadedly connected in the internal threaded hole. Limiting blocks (26) are symmetrically installed between the sliding frames (7) inside the moving rod (8). An extrusion block (27) is installed between the limiting blocks (26), and one end of the extrusion block (27) abuts against one end of the fixing screw (25).

8. The noodle packaging bag damage detection device based on vision detection according to claim 3, characterized in that: The upper end of the conveyor belt (2) is equipped with a positioning plate (3), and a positioning rod (5) is rotatably installed on one end of the positioning plate (3). The positioning rod (5) is installed on the fixing plate (4) by a threaded connection. The fixing plate (4) is fixed with threaded sleeves at equal intervals, and the fixing plate (4) is fixed to the outer wall of the guard plate.

Images