Intelligent detection device for defects of home textile products

Abstract

The invention discloses an intelligent home textile product defect detection device which comprises a rack, a conveying belt, an image acquisition assembly, a light source module, a control device and the like. The image acquisition assembly comprises at least two industrial cameras which are matched with the annular LED light source; a deep learning algorithm is built in the control device, images are received, defects are detected, and the speed of the conveying belt can be adjusted. The device is provided with a position sensor for triggering acquisition and comprises an alarm module and a storage module. The system can eliminate detection blind areas, improve the detection rate and identification efficiency of tiny defects, realize real-time monitoring alarm and data tracing, and meet the requirements of digital quality management.

Description

Technical Field

[0001] This invention relates to testing equipment, specifically an intelligent defect detection device for home textile products. Background Technology

[0002] In the production of home textile products, defect detection is a crucial step in ensuring product quality. Currently, the industry generally uses either manual inspection or traditional automated inspection equipment, which presents several technical challenges:

[0003] Manual inspection relies on the visual judgment of quality inspectors, and is affected by subjective factors such as fatigue and experience differences, which can affect the accuracy of 2mm inspections. 2 The following tiny holes, 5mm 2 The rate of missed detection for defects such as light-colored stains is as high as 15% to 20%, and each production line requires 68 quality inspectors, resulting in high labor costs. At the same time, the defect data recorded manually is scattered, making it difficult to achieve systematic traceability and analysis, which restricts targeted improvements to the production process.

[0004] Traditional automated inspection equipment often uses a single camera to capture images, combined with a direct light source. This can easily create blind spots due to lighting and shadows, resulting in an accuracy rate of less than 70% in identifying edge defects such as burrs and loose threads.

[0005] Currently, there is a need for intelligent detection devices for defects in home textile products. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to overcome the defects of the above-mentioned technologies and provide an intelligent detection device for defects in home textile products.

[0007] To solve the above-mentioned technical problems, the technical solution provided by the present invention is an intelligent detection device for defects in home textile products, including a frame, a conveyor belt, an image acquisition component, a light source module, a control device, a display screen, and a drive module;

[0008] The conveyor belt is horizontally mounted on the frame, and the drive module is connected to the conveyor belt to drive its operation.

[0009] The image acquisition component includes at least two industrial cameras, symmetrically arranged on the frame above the machine, with the industrial cameras facing the surface of the conveyor belt; the light source module is a ring-shaped LED light source, arranged around the industrial cameras;

[0010] The display screen is fixed to the control device; the control device is fixed to the frame.

[0011] The control device is electrically connected to the image acquisition component, the light source module, the drive module, and the display screen. It has a built-in deep learning-based defect recognition algorithm, which can receive home textile images acquired by industrial cameras and perform defect detection, identify defect types and location information, and control the drive module to adjust the conveyor belt speed. The display screen is used to display the detection results and statistical data in real time.

[0012] As an improvement, an alarm module is also included, which is electrically connected to the control device. When the number of detected defects exceeds a preset threshold, the alarm module will issue an audible and visual alarm.

[0013] The alarm module is fixed on the control device.

[0014] As an improvement, the industrial camera 8 is a high-definition CCD camera with a resolution of no less than 5 million pixels and a frame rate of ≥30fps.

[0015] As an improvement, the frame is equipped with an auxiliary rod, and a position sensor is mounted on the auxiliary rod. The position sensor is located at the entrance of the conveyor belt and is electrically connected to the control device. It is used to trigger the image acquisition component to start when the home textile product enters the detection area.

[0016] As an improvement, the control device is connected to a storage module for storing detection images and defect data, and supports data export function.

[0017] The advantages of this invention compared to existing technologies are: high-precision detection capability: employing at least two symmetrically arranged industrial cameras, combined with a ring LED light source illuminating at a 45° angle, eliminates blind spots and avoids shadow interference, significantly improving the detection accuracy for minute defects such as 2mm. 2 Hole, 5mm 2 Detection rate of stains.

[0018] The high-definition CCD camera has a resolution of ≥5 million pixels and a frame rate of ≥30fps. Combined with deep learning algorithms, it can identify more than 10 common home textile defects such as holes, stains, and frayed edges, achieving industry-leading detection accuracy.

[0019] Advantages of intelligent control: The deep learning-based control device can automatically identify the type and location of defects, dynamically adjust the conveyor belt speed, and perform slow-speed detailed inspection of high-defect products, thereby improving the reliability of inspection.

[0020] The position sensor enables precise triggering, avoiding invalid data collection. The system response time is ≤20ms, which greatly improves the detection efficiency. It can detect 3,000-5,000 home textile products per hour.

[0021] Real-time monitoring and alarm mechanism: The display screen shows defect images, location markers and statistical data in real time, and supports multi-parameter dynamic trend analysis to help operators keep abreast of production quality status.

[0022] The alarm module automatically triggers an audible and visual alarm when defects exceed the standard, with an alarm response time of less than 1 second, effectively preventing defective products from flowing into the next process and reducing enterprise losses.

[0023] Data management and traceability value: The storage module can store ≥1 million inspection records and supports multi-dimensional retrieval by time, type, size and other dimensions, providing data support for quality traceability and process improvement.

[0024] The data export function supports the generation of standardized reports that meet the requirements of the ISO9001 quality management system, helping enterprises achieve digital quality management transformation. Attached Figure Description

[0025] Figure 1 This is a schematic diagram of the structure of the present invention. Figure 1 .

[0026] Figure 2 This is a schematic diagram of the structure of the present invention. Figure 2 . Detailed Implementation

[0027] To facilitate understanding of this application, a more comprehensive description of this application will be provided below with reference to the accompanying drawings.

[0028] Referring to the attached diagram, the intelligent defect detection device for home textile products includes a frame 1, a conveyor belt 2, an image acquisition component 3, a light source module 4, a control device 5, a display screen 6, and a drive module 7.

[0029] The conveyor belt 2 is horizontally mounted on the frame 1, and the drive module 7 is connected to the conveyor belt 2 to drive its operation.

[0030] The image acquisition component 3 includes at least two industrial cameras 8, which are symmetrically arranged on the frame 12 above the frame 1, with the industrial cameras 8 facing the surface of the conveyor belt 2; the light source module 4 is a ring-shaped LED light source, which is arranged around the industrial cameras 8.

[0031] The display screen 6 is fixed to the control device 5; the control device 5 is fixed to the frame 12;

[0032] The control device 5 is electrically connected to the image acquisition component 3, the light source module 4, the drive module 7, and the display screen 6, respectively. It has a built-in deep learning-based defect recognition algorithm, which can receive home textile images acquired by the industrial camera 8 and perform defect detection, identify defect type and location information, and control the drive module 7 to adjust the speed of the conveyor belt 2. The display screen 6 is used to display the detection results and statistical data in real time.

[0033] It also includes an alarm module 9, which is electrically connected to the control device 5. When the number of detected defects exceeds a preset threshold, the alarm module 9 will issue an audible and visual alarm.

[0034] The alarm module 9 is fixed on the control device 5.

[0035] The industrial camera 8 is a high-definition CCD camera with a resolution of no less than 5 million pixels and a frame rate of ≥30fps.

[0036] The frame 12 is provided with an auxiliary rod 11, and a position sensor 10 is provided on the auxiliary rod 11. The position sensor 10 is located at the entrance of the conveyor belt 2 and is electrically connected to the control device 5. It is used to trigger the image acquisition component 3 to start when the home textile product enters the detection area.

[0037] The control device 5 is connected to a storage module for storing detection images and defect data, and supports data export function.

[0038] The present invention and its embodiments have been described above, and such description is not restrictive.

Claims

1. An intelligent defect detection device for home textile products, characterized in that: It includes a rack (1), a conveyor belt (2), an image acquisition component (3), a light source module (4), a control device (5), a display screen (6), and a drive module (7); The conveyor belt (2) is horizontally mounted on the frame (1), and the drive module (7) is connected to the conveyor belt (2) to drive its operation; The image acquisition component (3) includes at least two industrial cameras (8), which are symmetrically arranged on the frame (12) above the rack (1), with the industrial cameras (8) facing the surface of the conveyor belt (2); the light source module (4) is a ring LED light source, which is arranged around the industrial cameras (8); The display screen (6) is fixed on the control device (5); the control device (5) is fixed on the frame (12); The control device (5) is electrically connected to the image acquisition component (3), the light source module (4), the drive module (7) and the display screen (6) respectively. It has a built-in deep learning-based defect recognition algorithm, which can receive home textile images acquired by the industrial camera (8) and perform defect detection, identify defect type and location information, and control the drive module (7) to adjust the speed of the conveyor belt (2). The display screen (6) is used to display the detection results and statistical data in real time.

2. The intelligent defect detection device for home textile products according to claim 1, characterized in that: It also includes an alarm module (9), which is electrically connected to the control device (5). When the number of detected defects exceeds a preset threshold, the alarm module (9) issues an audible and visual alarm. The alarm module (9) is fixed on the control device (5).

3. The intelligent defect detection device for home textile products according to claim 1, characterized in that: The industrial camera (8) is a high-definition CCD camera with a resolution of no less than 5 million pixels and a frame rate of ≥30fps.

4. The intelligent defect detection device for home textile products according to claim 1, characterized in that: The frame (12) is provided with an auxiliary rod (11), and a position sensor (10) is provided on the auxiliary rod (11). The position sensor (10) is located at the entrance of the conveyor belt (2) and is electrically connected to the control device (5). It is used to trigger the image acquisition component (3) to start when the home textile product enters the detection area.

5. The intelligent defect detection device for home textile products according to claim 1, characterized in that: The control device (5) is connected to a storage module for storing detection images and defect data, and supports data export function.

Images