A fabric defect detection frame

Abstract

The utility model relates to textile detection technical field provides a kind of fabric defect detection frame, including support frame, the fabric defect detection frame further includes: macro lens camera, is set to the top of one side of the support frame;Four godets, two are a group and distribute in the two sides of the macro lens camera;A plurality of godet seats, are installed in the two sides of four godets;In the utility model, the support frame of the device setting adopts 3060, 3030 system aluminium section material to build, with portable and stable, and flexible, it is easy to adjust, four godets are divided into two groups, the clearance of cylinder in each group can be adjusted, effective cloth clamping is formed to different thicknesses of cloth, guarantee cloth stable when detecting, driving roller is processed by 5 ° taper, centripetal force is generated when rotating, effectively prevent cloth lateral displacement, improve detection accuracy, macro lens camera is matched with special base, can capture cloth tiny flaw, realize high-precision quality detection.

Description

Technical Field

[0001] This utility model relates to the field of textile testing technology, and in particular to a fabric defect detection rack. Background Technology

[0002] The textile industry is one of my country's important pillar industries. As the core form of textile products, fabric quality directly affects the market competitiveness of products and the economic benefits of enterprises. During the fabric production process, various defects inevitably occur due to factors such as raw material quality, production equipment precision, process parameter settings, and operator skills. These defects include warp breaks, weft breaks, oil stains, holes, color differences, and fuzz. These defects not only affect the appearance quality of the fabric but may also reduce its physical and performance properties, causing losses to downstream processing and end users. With the continuous improvement of market demands for fabric quality and the increasing automation of textile production, traditional manual inspection methods are no longer sufficient to meet the needs of modern production. In the past, fabric defect detection mainly relied on manual visual inspection. Inspectors observed the fabric surface with the naked eye and judged the presence, type, and severity of defects based on experience. While this method played a role in a certain historical period, its limitations have become increasingly apparent with the improvement of production efficiency and the increase in fabric varieties. In recent years, with the rapid development of machine vision technology, image processing technology, and artificial intelligence technology, automated fabric defect detection technology has gradually become a research hotspot and application trend. Automated detection equipment can acquire images of the fabric surface through image acquisition devices, and then use computers to process and analyze the images to achieve automatic identification and judgment of defects, thereby improving detection efficiency and accuracy, reducing labor costs, and providing a new solution for quality control in textile enterprises.

[0003] In existing technologies, some solutions employ manual inspection and traditional automated inspection. However, these solutions still have some problems. For example, the speed of manual inspection is limited by the visual fatigue and reaction speed of the inspectors. Generally, the speed of manual inspection is only a few meters per minute, which is difficult to adapt to the production speed of modern textile production lines, which is tens of meters per minute or even higher, easily causing production bottlenecks. The inspection results are greatly affected by subjective factors such as the inspector's experience, sense of responsibility, and emotions. Different inspectors may have different judgments on the same defect, and even the same inspector may have inconsistent judgments at different times, resulting in inconsistent inspection standards and frequent missed or false detections. Inspectors need to concentrate on observing the fabric surface for a long time, which can easily lead to visual fatigue, affecting not only the efficiency and accuracy of inspection but also harming the health of the inspectors. With the continuous rise in labor costs, large-scale adoption of manual inspection will significantly increase the production costs of enterprises and reduce their market competitiveness. Some traditional automated inspection equipment uses image acquisition devices with low resolution, poor lens optical performance, and unreasonable light source system design, resulting in poor quality of the acquired fabric images, making it difficult to clearly present subtle defects, and reducing inspection accuracy. Generally, defects larger than 0.5mm cannot meet the testing requirements of high-end fabrics. Existing automated testing equipment has poor adaptability to the material, color, and thickness characteristics of fabrics. When testing different types of fabrics, frequent manual adjustments to equipment parameters, such as camera exposure time and light source brightness, are required. This is cumbersome, and the adjustment effect is difficult to guarantee, easily leading to missed or false detections. The defect detection algorithms used by traditional automated testing equipment are mostly traditional image processing algorithms based on simple features. They have weak ability to identify complex defects, are not detailed enough in classifying defect types, and have poor anti-interference ability. When there are interference factors such as texture changes and stains on the fabric surface, the detection accuracy will drop significantly. Some traditional automated testing equipment lacks an effective intelligent control system, which cannot realize automatic adjustment and optimization of the testing process. When a defect is detected, it cannot issue an alarm signal and take corresponding measures in a timely manner, requiring manual intervention, which affects the continuity and automation of testing. Some existing equipment has limited storage capacity and lacks complete data management and analysis functions, making it impossible to store and effectively utilize test data for a long time. This makes it inconvenient for enterprises to trace the production process and analyze quality, and it is difficult to meet the needs of enterprises for refined management. Utility Model Content

[0004] The purpose of this invention is to address the problems in some existing automated inspection equipment where the image acquisition device has low resolution, poor lens optical performance, and unreasonable light source system design, resulting in poor quality of the acquired fabric images, difficulty in clearly presenting subtle defects, and inability to meet the inspection requirements of high-end fabrics. Furthermore, some existing automated inspection equipment has poor adaptability to the material, color, thickness, and other characteristics of fabrics.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a fabric defect detection frame, comprising a support frame, and further comprising:

[0006] A macro camera is mounted on the top of one side of the support frame;

[0007] Four rollers are arranged in groups of two on both sides of the macro camera.

[0008] Multiple idler roller seats are installed on both sides of the four idler rollers;

[0009] All four of the idler rollers are rotatably connected to multiple idler roller seats;

[0010] Four grooves are formed on both sides of the top of the support frame;

[0011] Multiple sliders are slidably installed inside the groove;

[0012] Two drive components are located within the four said grooves.

[0013] In a preferred embodiment, the driving component includes:

[0014] A bidirectional lead screw is rotatably mounted inside one of the grooves;

[0015] The bidirectional lead screw passes through two sliders, and the two bidirectional lead screws are threadedly connected to the two sliders.

[0016] A limiting rod is fixedly installed inside another of the aforementioned grooves;

[0017] The limiting rod passes through the two sliders, and the limiting rod slides with the two sliders.

[0018] An L-shaped groove is formed on one side of the slide groove;

[0019] A bevel gear one is installed at one end of the bidirectional lead screw;

[0020] A second bevel gear is disposed on one side of the first bevel gear;

[0021] The second bevel gear meshes with the first bevel gear, and both the first and second bevel gears are located inside the L-shaped groove.

[0022] The technical advantages of adopting the above-mentioned further solution are as follows: the threaded connection between the bidirectional lead screw and the slider can realize the synchronous reverse movement of the two sliders through rotation, and accurately adjust the spacing between the rollers to adapt to fabrics of different thicknesses; the sliding cooperation between the limit rod and the slider restricts the rotation of the slider and ensures that it moves stably along the slide groove; the meshing transmission of bevel gear one and bevel gear two turns the power direction by 90 degrees, and with the spatial layout of the L-shaped groove, the drive structure is compact and the transmission efficiency is high, avoiding the occupation of the detection area space.

[0023] In a preferred embodiment, the driving component further includes:

[0024] The rotating shaft is fixedly installed in the middle of the second bevel gear;

[0025] The rotating shaft passes through one side of the support frame and is rotatably connected to the support frame.

[0026] The motor is mounted on one side of the support frame;

[0027] The output end of the motor is connected to one end of the rotating shaft via a coupling.

[0028] The technical advantages of adopting the above-mentioned further solution are as follows: the motor drives the rotating shaft to rotate through the coupling, and transmits the power to the bidirectional lead screw through the bevel gear transmission, realizing the electric adjustment of the roller spacing, replacing manual operation, and the adjustment accuracy can reach ±0.1mm; the rotational connection between the rotating shaft and the support frame ensures stable power transmission, reduces mechanical loss, and improves the durability of the drive system.

[0029] In a preferred embodiment, the fabric defect detection rack further includes:

[0030] Two active roller seats are installed on both sides of the top of the support frame;

[0031] The active roller is rotatably mounted between the two active roller seats.

[0032] The technical effects of adopting the above-mentioned further solution are as follows: the two active roller seats provide stable support for the active roller, ensuring its coaxiality during rotation and avoiding fabric conveying deviation caused by shaft shaking; as the core component of fabric conveying, the active roller realizes continuous and uniform movement of the fabric through rotation, providing a stable detection benchmark for line-by-line scanning of the macro camera.

[0033] In a preferred embodiment, the fabric defect detection rack further includes:

[0034] A motor connector is installed on one side of the support frame;

[0035] Two synchronous pulleys are respectively rotatably mounted on one side of the drive roller and the motor connecting seat;

[0036] The active roller is connected to the timing pulley at the top via a connecting shaft and fastening screws.

[0037] Two belts are fitted between the two synchronous pulleys.

[0038] The technical advantages of adopting the above-mentioned further solution are: the motor connecting seat provides an installation reference for the bottom synchronous pulley, ensuring that it remains parallel to the synchronous pulley on the drive roller; the transmission combination of the synchronous pulley and the synchronous belt has the characteristics of smooth transmission, low noise, and convenient maintenance, and can efficiently transmit the motor power to the drive roller, ensuring the stability of the fabric conveying speed.

[0039] In a preferred embodiment, the fabric defect detection rack further includes:

[0040] A brushless motor is mounted on one side of the motor connector.

[0041] The output end of the brushless motor is connected to the synchronous pulley at the bottom via a key and fastening screw.

[0042] The technical advantages of adopting the above-mentioned further solutions are: the brushless motor has the characteristics of high speed accuracy, low heat generation and long life, and the bolt connection between its output end and the bottom synchronous pulley facilitates disassembly and maintenance; by adjusting the speed of the brushless motor, the fabric conveying speed can be precisely controlled, adapting to the detection needs of different fabric materials and avoiding image blurring caused by excessive speed.

[0043] In a preferred embodiment, the fabric defect detection rack further includes:

[0044] Two macro camera bases are mounted on both sides of the top of the support frame;

[0045] The macro camera is located between the two support frames.

[0046] The technical effects of adopting the above-mentioned further solution are as follows: the two macro camera bases provide rigid support for the macro camera, ensuring that the camera lens maintains a constant distance from the fabric surface and avoiding imaging focal length deviation caused by camera shaking; the fixed installation method of the base stabilizes the camera position, ensures the consistency of images detected in different batches, and improves the reliability of algorithm recognition.

[0047] In a preferred embodiment, the fabric defect detection rack further includes:

[0048] An industrial computer is mounted at the bottom of the support frame;

[0049] The industrial computer is connected to the macro camera via a high-speed data transmission interface, receives a large amount of image data collected by the macro camera in real time, and runs a defect detection algorithm to analyze and process the images.

[0050] The technical effects of adopting the above-mentioned further solutions are as follows: the high-performance hardware of the industrial computer can process the massive image data transmitted by the macro camera in real time, and realize automatic identification and analysis through defect detection algorithms, replacing manual interpretation; the high-speed data transmission interface ensures that the image data is transmitted without delay, and together with the algorithm processing capabilities, the detection system can adapt to the high-speed operation of the production line, while providing hardware support for data storage, traceability and process optimization.

[0051] Compared with the prior art, the advantages and positive effects of this utility model are as follows:

[0052] 1. This utility model features a support frame constructed from 3060 and 3030 series aluminum profiles, combining lightweight and stability with flexible assembly and easy adjustment. The four rollers are divided into two groups, and the gap between the rollers in each group can be adjusted to effectively clamp fabrics of different thicknesses, ensuring fabric stability during testing. The active roller is machined with a 5° taper, generating a centripetal force during rotation, effectively preventing lateral fabric displacement and improving testing accuracy. A macro camera paired with a dedicated base can capture minute fabric defects, achieving high-precision quality inspection. This makes the overall device, from its structure to its component design, provide a more stable and accurate solution for fabric inspection.

[0053] 2. This utility model features a high-resolution industrial macro line array camera, capable of clearly capturing minute defects on the fabric surface with a detection accuracy below 0.1mm, effectively improving the accuracy of defect detection. Secondly, the camera parameters can be automatically adjusted according to fabric characteristics, achieving adaptive image acquisition for fabrics of different materials, colors, and thicknesses, expanding the device's applicability. It integrates the advantages of deep learning and traditional image processing algorithms, employing different detection strategies for different types of defects, improving the speed and accuracy of defect detection. Furthermore, the algorithm has been optimized and accelerated, enabling real-time operation on industrial computers, meeting the high-speed inspection needs of production lines. Simultaneously, by continuously updating and expanding the defect sample library, the algorithm's detection performance can be continuously improved. An intelligent control system has been constructed, achieving automated control of the entire process, including fabric conveying, image acquisition, and defect detection. The system can automatically adjust the device's operating parameters based on real-time detection data, ensuring the stability and reliability of the detection process. Attached Figure Description

[0054] Figure 1 This is a perspective view of an embodiment of this application;

[0055] Figure 2This is a perspective view of an embodiment of this application;

[0056] Figure 3 This is a perspective cross-sectional view of an embodiment of this application;

[0057] Figure 4 This is an embodiment of the present application. Figure 3 Enlarged view of point A;

[0058] Figure 5 This is a perspective cross-sectional view of an embodiment of this application.

[0059] Legend:

[0060] 1. Support frame; 2. Drive roller; 3. Drive roller seat; 4. Synchronous pulley; 5. Same belt; 6. Motor connecting seat; 7. Macro camera base; 8. Macro camera; 9. Idler roller; 10. Idler roller seat; 11. Slider; 12. Bidirectional lead screw; 13. Slide groove; 14. Bevel gear one; 15. Bevel gear two; 16. L-shaped groove; 17. Rotating shaft; 18. Motor; 19. Limiting rod; 20. Industrial computer; 21. Brushless motor. Detailed Implementation

[0061] The technical solutions of the present utility model will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present utility model, and not all embodiments. Based on the embodiments of the present utility model, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of the present utility model.

[0062] Example 1:

[0063] Please see Figures 1-5 This embodiment provides a fabric defect detection rack, the specific idea of ​​which is as follows:

[0064] A fabric defect detection frame includes a support frame 1, and the fabric defect detection frame also includes: a macro camera 8, four idler rollers 9, multiple idler roller seats 10, four slides 13, multiple sliders 11 and two drive components.

[0065] The macro camera 8 is located on the top of one side of the support frame 1.

[0066] It should be noted that the macro camera 8 adopts an industrial-grade macro line scan camera, uses a 10 Gigabit Ethernet interface, and integrates the sensor, light source, and lens into one design. Its transmission rate can meet the requirements of most industrial applications. It can work stably in various harsh environments and can detect continuously moving materials, such as metals, plastics, paper, and fibers. The objects being detected are usually moving at a uniform or variable speed. The macro camera 8 scans them line by line to achieve uniform detection of their entire surface.

[0067] In addition, the macro camera 8 has four light source settings: time-division strobe off, two-way strobe, three-way strobe, and single backlight mode. The current built-in light source brightness is fixed. The exposure brightness of the image is controlled by controlling the exposure time (the time the lights are on for a single line of acquisition). Users need to set the single-line exposure time according to the actual situation. Under normal circumstances, when time-division strobe is not enabled, the single acquisition process includes one trigger and the control of the lights on both sides (A+B). In the two-way strobe mode, the A-side light lights up first to trigger once in a single acquisition, and the B-side light lights up later to trigger once. High and low brightness and angle exposure can be set.

[0068] The four rollers 9 are arranged in two groups on both sides of the macro camera 8.

[0069] In addition, the distance between the two idler rollers 9 can be adjusted to facilitate clamping fabrics of different thicknesses.

[0070] Among them, the multiple idler roller seats 10 that play a role in installation are all installed on both sides of the four idler rollers 9, and the four idler rollers 9 are rotatably connected to the multiple idler roller seats 10.

[0071] The four sliding grooves 13 are located on both sides of the top of the support frame 1.

[0072] The multiple sliders 11 are all slidably installed inside the slide groove 13.

[0073] The two drive components are located within the four slides 13.

[0074] As examples, in this embodiment, the driving components include: a bidirectional lead screw 12, a limiting rod 19, an L-shaped groove 16, a first bevel gear 14, a second bevel gear 15, a rotating shaft 17, and a motor 18.

[0075] The bidirectional lead screw 12, which serves to adjust the distance, is rotatably installed inside one of the slide grooves 13.

[0076] In addition, the two-way lead screw 12 passes through the two sliders 11, and the two two-way lead screws 12 are threadedly connected to the two sliders 11.

[0077] The limiting rod 19, which serves as a limit, is fixedly installed inside another slide groove 13.

[0078] In addition, the limiting rod 19 passes through the two sliders 11, and the limiting rod 19 slides with the two sliders 11.

[0079] The L-shaped groove 16 is provided on one side of the slide groove 13.

[0080] The bevel gear 14 is installed at one end of the double-acting lead screw 12.

[0081] The second bevel gear 15 is located on one side of the first bevel gear 14.

[0082] It should be noted that bevel gear 15 meshes with bevel gear 14, and both bevel gear 14 and bevel gear 15 are located inside the L-shaped groove 16.

[0083] The rotating shaft 17 is fixedly installed in the middle of the bevel gear 15.

[0084] In addition, the rotating shaft 17 passes through one side of the support frame 1, and the rotating shaft 17 is rotatably connected to the support frame 1.

[0085] The motor 18, which plays a driving role, is installed on one side of the support frame 1, and the output end of the motor 18 is connected to one end of the rotating shaft 17 through a coupling.

[0086] In this embodiment, the support frame 1 is constructed from 3060 and 3030 series aluminum profiles. The distance between the two rollers 9 of the two sets can be flexibly adjusted by the drive component, thereby forming a clamping mechanism for fabrics of different thicknesses. The multi-mode light source of the macro camera 8 adapts to the reflective characteristics of different materials, solving the imaging problem of highly reflective or dark fabrics.

[0087] Example 2:

[0088] Please see Figures 1-5 Based on Example 1, this example provides a fabric defect detection rack, the specific concept of which is as follows:

[0089] The fabric defect detection rack also includes: two active roller seats 3, an active roller 2, a motor connecting seat 6, two synchronous pulleys 4, a synchronous belt 5, a brushless motor 21, two macro camera bases 7, and an industrial computer 20.

[0090] The two active roller seats 3 are installed on both sides of the top of the support frame 1.

[0091] The active roller 2 is rotatably mounted between two active roller seats 3.

[0092] It should be noted that the active roller is machined with a 5° taper, which generates a centripetal force when rotating, effectively preventing the fabric from shifting laterally.

[0093] The motor connector 6 is installed on one side of the support frame 1.

[0094] The two synchronous pulleys 4 are respectively rotatably mounted on one side of the drive roller 2 and the motor connecting seat 6.

[0095] Among them, the two synchronous belts 5 are set between the two synchronous pulleys 4.

[0096] In addition, the active roller 2 is connected to the timing pulley 4 located at the top via a connecting shaft and fastening screws.

[0097] The brushless motor 21 is installed on one side of the motor connector 6, and the output end of the brushless motor 21 is connected to the synchronous pulley 4 at the bottom with a key and fastening screw.

[0098] The two macro camera bases 7 are installed on both sides of the top of the support frame 1, and the macro camera 8 is located between the two support frames 1.

[0099] The industrial computer 20 is located at the bottom of the support frame 1.

[0100] It should be noted that the industrial computer 20 is equipped with a high-performance processor, large-capacity memory, and high-speed solid-state drive, possessing powerful data processing capabilities. The industrial computer 20 connects to the macro camera 8 via a high-speed data transmission interface, receiving large amounts of image data captured by the camera in real time and running defect detection algorithms to analyze and process the images. The computer is also responsible for controlling the operation of the entire device, including adjusting the fabric conveying speed, controlling the light source brightness, and communicating with external devices. Simultaneously, the computer has a built-in data storage device using a large-capacity disk array, capable of storing fabric defect detection data for months or even years, including raw image data and processed defect information. The data storage device has data backup and recovery functions, periodically backing up important data to external storage media to prevent data loss. Furthermore, through network sharing, authorized personnel can remotely access the storage device to query and analyze historical detection data.

[0101] It is important to note that the fabric defect detection device has an external controller. This controller uses a programmable logic controller (PLC) as its core control unit, responsible for coordinating the actions of various parts of the device. The PLC receives signals from sensors, such as fabric position sensors and tension sensors, and controls the operation of motors, light sources, and other equipment according to a preset program. For example, when the fabric position sensor detects fabric deviation, the PLC immediately controls the correction device to adjust the fabric, ensuring that the fabric is always centered in the image acquisition area.

[0102] In this embodiment, when the fabric enters the detection area of ​​the macro camera 8, the bases 7 of the two macro cameras 8 provide stable support for the macro camera 8 (located between the two bases). The macro camera 8 starts scanning according to preset parameters: when the time-division strobe is not enabled, a single acquisition triggers the simultaneous lighting of the lights on both sides A and B, completing one line of image acquisition; when the two-way strobe is enabled, the light on side A lights up first and triggers acquisition, and the light on side B lights up later and triggers acquisition again, highlighting minute defects through high and low brightness / angle exposure; the acquired image data is transmitted in real time to the industrial computer 20 through a high-speed data transmission interface (such as a 10 Gigabit Ethernet interface). The industrial computer 20 utilizes a high-performance processor and large-capacity memory. The fast-running defect detection algorithm first preprocesses the image (grayscale conversion, filtering, and noise reduction) to remove fabric texture interference; then, the algorithm identifies defects such as broken warp, broken weft, stains, and holes, and marks the location, type, and size of the defects; the detection results (including defect information and the original image) are stored in real time to a large-capacity disk array and displayed on the industrial computer 20 interface for easy viewing by operators. The macro camera 8, fixed on a dedicated base, has a stable acquisition position. Combined with multi-mode light sources and adjustable exposure time, it can clearly capture minute defects smaller than 0.1 mm (such as broken threads and small stains), improving the detection accuracy by more than 50% compared to traditional automated equipment.

[0103] Working principle:

[0104] In use, start the two drive units, the two motors 18 drive the two bidirectional lead screws 12 to rotate, the two bidirectional lead screws 12 drive the two sliders 11 above to move away from each other, and at the same time the two sliders 11 slide on the limit rod 19 to widen the gap between the two idler rollers 9. Then stop the drive, and then manually pass the fabric from bottom to top through the gap between the two idler rollers 9 on the right side, and then from top to bottom through the gap between the two idler rollers 9 on the left side. Then start the two drive units again, the two motors 18 drive the two sliders 11 to move closer to each other, and at the same time drive the other two sliders 11 to slide on the limit rod 19, so that fabrics of different thicknesses can be clamped, and finally the fabric is fixed on the drive roller 2.

[0105] Start the brushless motor 21. The brushless motor 21 starts to rotate, which drives the upper synchronous pulley 4 to rotate. The synchronous pulley 4 drives the same belt 5 to rotate. The same belt 5 drives the lower synchronous pulley 4 to rotate, which makes the drive roller 2 start to rotate. This causes the fabric on top to start to move. Under the clamping of the idler rollers 9, the fabric is stretched on the two inner idler rollers 9 to form a plane.

[0106] Once the macro camera 8 is activated, it can correctly identify the center area of ​​the plane. Although the fabric is taut from both sides, it can still move steadily to the left under the drive of the brushless motor 21, thus forming a stable image on the macro camera 8. The collected data is then sent to the industrial computer 20. After receiving the image data, the industrial computer 20 first performs preprocessing on the image, including grayscale conversion, filtering, and noise reduction, to improve the image's clarity and contrast and highlight defect features. Then, it runs defect detection software based on deep learning or traditional image processing algorithms to detect defects on the fabric.

[0107] All standard parts used in this utility model can be purchased from the market, and irregular parts can be customized according to the description and drawings. The specific connection methods of each part adopt conventional methods such as bolts, rivets, and welding that are mature in the prior art. The machinery, parts and equipment adopt conventional models in the prior art. In addition, the circuit connection adopts conventional connection methods in the prior art, which will not be described in detail here. The contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0108] The above description is merely a preferred embodiment of the present utility model and is not intended to limit the present utility model in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments for application in other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present utility model without departing from the technical solution of the present utility model shall still fall within the protection scope of the present utility model.

Claims

1. A fabric defect detection frame, comprising a support frame (1), characterized in that, The fabric defect detection rack also includes: A macro camera (8) is mounted on the top of one side of the support frame (1); Four rollers (9) are distributed on both sides of the macro camera (8) in two groups; Multiple idler roller seats (10) are installed on both sides of the four idler rollers (9); Among them, all four idler rollers (9) are rotatably connected to multiple idler roller seats (10); Four grooves (13) are provided on both sides of the top of the support frame (1); Multiple sliders (11) are slidably installed inside the groove (13); Two drive components are located within the four said grooves (13); The driving component includes: a bidirectional lead screw (12) rotatably mounted inside one of the slide grooves (13); wherein the bidirectional lead screw (12) passes through two sliders (11), and the two bidirectional lead screws (12) are threadedly connected to the two sliders (11); The limiting rod (19) is fixedly installed inside another of the slide grooves (13); The limiting rod (19) passes through the two sliders (11), and the limiting rod (19) slides with the two sliders (11); An L-shaped groove (16) is formed on one side of the slide groove (13); A bevel gear (14) is installed at one end of the bidirectional lead screw (12); Bevel gear two (15) is disposed on one side of bevel gear one (14); The second bevel gear (15) meshes with the first bevel gear (14), and both the first bevel gear (14) and the second bevel gear (15) are located inside the L-shaped groove (16).

2. The fabric defect detection rack according to claim 1, characterized in that, The driving component also includes: The rotating shaft (17) is fixedly installed in the middle of the bevel gear (15); The rotating shaft (17) passes through one side of the support frame (1), and the rotating shaft (17) is rotatably connected to the support frame (1); A motor (18) is mounted on one side of the support frame (1); The output end of the motor (18) is connected to one end of the shaft (17) via a coupling.

3. The fabric defect detection rack according to claim 1, characterized in that, The fabric defect detection rack also includes: Two active roller seats (3) are installed on both sides of the top of the support frame (1); The active roller (2) is rotatably mounted between the two active roller seats (3).

4. A fabric defect detection rack according to claim 3, characterized in that, The fabric defect detection rack also includes: The motor connector (6) is installed on one side of the support frame (1); Two synchronous pulleys (4) are respectively rotatably mounted on one side of the drive roller (2) and the motor connecting seat (6); The active roller (2) is connected to the synchronous pulley (4) located at the top via a connecting shaft and fastened with screws. Two synchronous belts (5) are fitted between the two synchronous pulleys (4).

5. A fabric defect detection rack according to claim 4, characterized in that, The fabric defect detection rack also includes: A brushless motor (21) is mounted on one side of the motor connector (6); The output end of the brushless motor (21) is connected to the synchronous pulley (4) at the bottom with a key and fastening screw.

6. A fabric defect detection rack according to claim 1, characterized in that, The fabric defect detection rack also includes: Two macro camera bases (7) are mounted on both sides of the top of the support frame (1); The macro camera (8) is located between the two support frames (1).

7. A fabric defect detection rack according to claim 1, characterized in that, The fabric defect detection rack also includes: An industrial computer (20) is disposed at the bottom of the support frame (1); The industrial computer (20) is connected to the macro camera (8) through a high-speed data transmission interface, receives a large amount of image data collected by the macro camera (8) in real time, and runs a defect detection algorithm to analyze and process the images.

Images