Frame stranding surface defect detection device based on machine vision

Abstract

The invention provides a frame-stranded surface defect detection device based on machine vision, which belongs to the field of cable surface defect detection and is composed of a metal shell, an image acquisition unit, a detection unit and a supporting structure. Cable quality detection equipment is supported to move up and down, the acquisition frequency of a camera is adaptively adjusted according to the linear speed, uniform lighting and clear cable surface information imaging in the process that a cable penetrates through an image acquisition unit are guaranteed, and the method can be applied to defect detection of other types of materials through proper adjustment and optimization; real-time monitoring and data analysis of the cable production process can be achieved, timely and accurate production data are provided for production managers, the managers are helped to find production anomalies and problems in time, and therefore the production scheme is adjusted in time, and the product quality and the production efficiency are guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of cable surface defect detection, and in particular to a frame-stranded surface defect detection device based on machine vision. Background Art

[0002] In the manufacturing of wires and cables, the twisting process involves spirally winding multiple conductors or cable cores according to a specific pitch and twisting pattern to form a composite wire core with a compact structure, high mechanical strength, and stable electrical conductivity. This process requires strict control of the single-filament tension, twisting direction, and pitch ratio to ensure the roundness, tensile strength, and electrical continuity of the finished wire core. However, due to factors such as mechanical vibration, metal fatigue, and fluctuations in single-filament quality during the high-speed twisting process, defects such as peeling, wire breakage, and uneven twisting can easily occur, resulting in reduced conductivity and mechanical strength of the wire core, and even posing safety hazards. Traditional wire break detection relies on manual visual inspections or single photoelectric switches, which suffer from response lag, the inability to detect wire breaks as low as 0.1 seconds, a high false detection rate, and data non-traceability. According to statistics, the manual missed detection rate is as high as 15%-25%, directly resulting in material loss and waste of production capacity.

[0003] With the deep integration of artificial intelligence, machine vision, and multimodal sensing technologies, quality inspection in cable manufacturing has entered a new era of high-precision, fully automated development. A new generation of intelligent inspection systems, integrating high-resolution industrial cameras, multispectral imaging modules, and fiber optic sensor networks, combined with deep learning algorithms, enables real-time detection and intelligent diagnosis of surface defects in frame-stranded cables. This system not only accurately identifies traditional defects such as broken wires and peeling, but also measures strand pitch and lay direction through traditional image analysis. The system boasts an overall defect detection rate exceeding 99.5%, with a false alarm rate below 0.8%. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention provides a frame-twisting surface defect detection device based on machine vision to realize the automated detection of defects in the cable frame-twisting process.

[0005] The technical solution of the present invention is:

[0006] A machine vision-based frame strand surface defect detection device comprises a metal shell, an image acquisition unit, a detection unit, and a support structure.

[0007] The metal housing, with an anti-reflective finish, primarily shields the exterior from light, minimizing the impact of complex ambient lighting on the image quality of the product under inspection. The interior is painted with a light-absorbing, low-reflectivity material. Circular openings are located on both sides of the housing, along the cable's direction. These openings should be appropriately sized to prevent scratches on the cable.

[0008] The image acquisition unit, consisting of a camera assembly, a light source assembly, and a camera trigger assembly, primarily comprises an industrial camera, lens, light source, encoder, and encoder wheel. A pair of tunnel light sources illuminates the cables, creating a diffuse, shadowless lighting effect. This ensures uniform 360° lighting throughout the cable, minimizing the impact of uneven lighting on defect detection.

[0009] In the image acquisition unit, the camera is fixed with a long screw hole, and the camera can be moved back and forth by loosening or tightening the screws. It uses an electric focus lens to automatically adjust the focal length to adapt to different production lines and wire diameters.

[0010] The detection unit includes an industrial computer, a display, and an alarm located below the device. The industrial computer is equipped with defect detection algorithms and programs. The display and alarm output defect detection results in predefined formats, including graphics, text, and audio.

[0011] The support structure adopts an open-close design, with round holes reserved on the sides to ensure that the equipment can be online and offline at any time. The opening and closing adopts a manual opening and closing + push rod method, ensuring that the opening and closing is labor-saving and the cover can be kept open.

[0012] The supporting structure includes a keyboard tray, a telescopic cover, a lifting push rod, a guide assembly, and a lifting wheel column;

[0013] The keyboard tray is placed on the fixed rod;

[0014] The telescopic cover is mainly used to protect the equipment and prevent damage to the equipment lifting structure;

[0015] The lifting push rod is arranged inside the metal shell and is used to raise and lower the height of the head assembly to adapt to production lines of different heights;

[0016] The guide assembly is used to ensure the precise guidance and positioning of the lifting push rod during movement, ensuring the stability and accuracy of the equipment;

[0017] The lifting wheel column is used to support the camera trigger assembly and can be adjusted in height to suit different production lines.

[0018] Four universal wheels can be installed under the entire device to facilitate forward and backward movement and fixation.

[0019] The beneficial effects of the present invention are

[0020] The opening and closing design of the image acquisition device supports the cable quality detection equipment to be installed and removed at any time, making it convenient for users to use.

[0021] The industrial linear array camera is triggered by an encoder, which can adaptively adjust the camera acquisition frequency according to the linear speed to ensure the acquisition of complete images.

[0022] A pair of tunnel light sources is used to ensure uniform lighting of the cable as it passes through the image acquisition unit and clear imaging of the cable surface information.

[0023] This device is not only suitable for the production process of slender materials such as metal wires and fibers, but can also be applied to defect detection of other types of materials through appropriate adjustment and optimization. It has strong versatility and scalability. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a schematic diagram of the overall structure of the present invention;

[0025] Figure 2 It is a left-side structural schematic diagram of the present invention;

[0026] Figure 3 This is a schematic diagram of the connection between the lifting wheel column and the camera trigger assembly. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0028] The present invention provides a machine vision-based cable stranding surface defect detection device, addressing the problem of detecting surface quality defects during the stranding process. The cable stranding surface defect detection device disclosed herein consists of a metal housing, an image acquisition unit, a detection unit, and a support structure. The metal housing, with an anti-reflective finish, utilizes an electric focus lens for automatic focal length adjustment. A light source fixture secures the image acquisition unit's light source. The image acquisition unit includes a camera assembly, a light source assembly, and a camera trigger assembly, primarily comprising an industrial camera, lens, encoder, encoder wheel, and light source, and is used to capture images of stranded wire during production. The image acquisition system, primarily composed of a pair of tunnel light sources and an industrial linear array camera, ensures uniform lighting as the cable passes through the defect detection device. The detection unit, primarily comprising an industrial computer, a display, and an alarm, analyzes and processes the stranded wire images captured by the image acquisition unit and outputs the processed results for easy viewing on the display. The industrial computer uses a defect detection algorithm to analyze and process the images captured by the image acquisition unit, while the display and alarm output the processed results in a predefined format. The defect detection device adopts an open-and-close design as a whole, with round holes reserved on each side to ensure that the defect detection device can be put on and off the line at any time.

[0029] The structure of the present invention is as follows Figure 1 shown.

[0030] The metal shell adopts an open-close design, which is divided into ① bottom box assembly and ② head assembly. A hole is opened in the middle of the head assembly to detect the stranded wire during the production process.

[0031] The image acquisition unit mainly includes ③ camera components, ④ light source group and Camera trigger assembly, twisted wire passing through Enter the middle opening of ② and drive The encoder wheel rotates, which drives the encoder to rotate and trigger the camera. ④A pair of tunnel light sources are fixed to the inside of ① with screws. A hole is opened in the middle to facilitate camera image acquisition. ④ are arranged on both sides of the twisted wire to evenly illuminate the twisted wire and ensure clear image acquisition.

[0032] The inspection unit consists of an alarm (⑤), a display (⑥), and an industrial computer (⑩). These are secured to the upper half of the metal housing using a mounting rod. The alarm is embedded in the head assembly (②), with an internal audible alarm and an external light alarm for workers to quickly detect. The industrial computer (⑩) is located in an industrial computer cabinet beneath the base assembly (①). The display and alarm output defect detection results in predefined formats, including graphics, text, and audio.

[0033] The supporting structure includes ⑦ keyboard tray, ⑧ telescopic cover, ⑨ lifting push rod, Guide components, Lifting wheel column. ⑦The keyboard tray and ⑥monitor are placed together on the fixed rod; ⑧The telescopic cover is mainly used to protect the equipment and prevent damage to the equipment lifting structure; ⑨The lifting push rod is arranged inside the ① bottom box assembly and is used to raise and lower the height of the ②head assembly to adapt to production lines of different heights; The guide assembly is used to ensure the precise guidance and positioning of the lifting push rod during movement, ensuring the stability and accuracy of the equipment; The lifting wheel column is used to support The camera trigger assembly can be adjusted in height to suit different production lines.

[0034] Compared to traditional manual inspection, this machine vision-based defect detection device offers higher accuracy and stability, reduces the impact of subjective factors on test results, and significantly improves the automation level of the production line. Furthermore, this device enables real-time monitoring and data analysis of the cable production process, providing production managers with timely and accurate production data, helping them to promptly identify production anomalies and problems, allowing them to adjust production plans and ensure product quality and efficiency.

[0035] In general, the frame-stranded surface defect detection device based on machine vision technology is an efficient, accurate and reliable quality control tool, which plays an important role in promoting the development of the cable production industry.

[0036] The above description is only a preferred embodiment of the present invention and is only used to illustrate the technical solution of the present invention, and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention are included in the scope of protection of the present invention.

Claims

1. A machine vision-based frame strand surface defect detection device, characterized in that: include: The metal shell is an anti-reflective shell, including the bottom box assembly and the head assembly, and the interior is composed of a high-contrast background board; Image acquisition unit, used to collect images of twisted wires during production; The detection unit is used to analyze and process the twisted wire images collected by the image acquisition unit, and output the processing results for the convenience of staff to view on the display.

2. The device according to claim 1, characterized in that It also includes a supporting structure for adjusting the height of the equipment, supporting each unit of the equipment, and ensuring the normal use of the equipment.

3. The device according to claim 2, characterized in that The supporting structure includes a keyboard tray, a telescopic cover, a lifting push rod, a guide assembly, and a lifting wheel column; The keyboard tray is placed on the fixed rod; The telescopic cover is mainly used to protect the equipment and prevent damage to the equipment lifting structure; The lifting push rod is arranged inside the metal shell and is used to raise and lower the height of the head assembly to adapt to production lines of different heights; The guide assembly is used to ensure the precise guidance and positioning of the lifting push rod during movement, ensuring the stability and accuracy of the equipment; The lifting wheel column is used to support the camera trigger assembly and can be adjusted in height to suit different production lines.

4. The device according to claim 1, characterized in that The metal shell is designed to be open and close, with a hole in the middle of the head assembly to detect the stranded wire during the production process.

5. The device according to claim 1, characterized in that The image acquisition unit includes an industrial camera, lens, light source, encoder, and encoding wheel. The encoding wheel is driven by twisted wire to rotate, and the encoding wheel drives the encoder to rotate, triggering the industrial camera. A pair of tunnel light sources are arranged on both sides of the cable, and a hole is opened in the middle for the camera to capture the cable image, ensuring uniform lighting of the cable when passing through the image acquisition unit, and ensuring clear imaging of the cable surface information.

6. The device according to claim 1, characterized in that The detection unit is fixed to the upper part of the metal shell using a fixing rod, including the industrial computer, display and alarm arranged below; the alarm is embedded in the head assembly, with the sound alarm on the inside and the light alarm on the outside for workers to observe the alarm information in time; the industrial computer is placed in the industrial computer cabinet set below the bottom box assembly.

7. The device according to claim 6, characterized in that The industrial computer is responsible for analyzing and processing the images collected by the image acquisition unit using the defect detection algorithm.

8. The device according to claim 6, characterized in that The display and alarm output the defect detection results in a predefined form, including outputting the recognition results in the form of graphics, text and sound.

Images