Cable cage stranding process defect detection device based on artificial intelligence machine vision

Abstract

The invention discloses a cable cage stranding process defect detection device based on artificial intelligence machine vision, and belongs to the technical field of cable surface defect detection.The cable cage stranding process defect detection device comprises a shading shell, an image acquisition unit, a defect detection unit and a supporting structure, the image acquisition unit is arranged in the shading shell, and a cable via hole is formed in the shading shell; the image acquisition unit comprises an industrial camera, a lens and a light source; the light source comprises a point light source arranged right above the cable, and the point light source is used for ensuring uniform lighting when the cable passes through the image acquisition unit; the arched light source is arranged on the lower side of the cable, a hole is formed in the middle of the arched light source for installing an industrial camera and a lens, and the arched light source is used for ensuring obvious cable surface information imaging; and the defect detection unit comprises an industrial personal computer, a display and an alarm. The detection precision can be improved, the detection stability is ensured, and the automation level of a production line is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cable surface defect detection, and particularly to a defect detection device for cable cage stranding process based on artificial intelligence machine vision. Background Art

[0002] In the process of wire and cable manufacturing, the cage stranding process is to twist and reinforce multiple strands of conductors or cable cores in a specific way to increase their mechanical strength and circuit capacity. However, due to complex mechanical operations and quality differences of wire materials, defects such as broken wires may occur during the cage stranding process, posing a threat to the quality and safety of wire and cable. Traditional methods for detecting broken wires in cage stranding mainly rely on manual visual inspection. This method is not only inefficient but also easily affected by human factors, with high false detection rate and missed detection rate.

[0003] With the rapid development of artificial intelligence technology, using machine vision technology to replace manual measurement and judgment of images has achieved remarkable breakthroughs. This device uses advanced artificial intelligence algorithms and machine vision technology to quickly and accurately identify possible defects in the cable cage stranding process, including problems such as broken wires, short circuits, and poor contact, effectively improving the quality control level on the production line. However, the current defect detection device technology based on artificial intelligence is not yet mature, with problems such as poor detection accuracy, difficult operation, and unstable use. Summary of the Invention

[0004] The technical task of the present invention is to provide a defect detection device for cable cage stranding process based on artificial intelligence machine vision, which can improve the detection accuracy, ensure the stability of detection, and greatly enhance the automation level of the production line.

[0005] The technical solution adopted by the present invention to solve its technical problems is:

[0006] A defect detection device for cable cage stranding process based on artificial intelligence machine vision includes a light-shielding housing, an image acquisition unit, a defect detection unit, and a support structure.

[0007] The light-shielding housing is an upper and lower opening and closing structure, and the light-shielding housing is fixed through the support structure and realizes opening and closing fixation; the image acquisition unit is arranged inside the light-shielding housing, and a cable through-hole is opened on the light-shielding housing to support the cable to go online and offline at any time.

[0008] The image acquisition unit includes an industrial camera, a lens, and a light source; the light source includes:

[0009] A point light source arranged above the cable, with a hole opened in the middle to install the industrial camera and the lens, and the point light source is used to ensure uniform lighting during the process of the cable passing through the image acquisition unit.

[0010] An arched light source is arranged below the cable. An industrial camera and a lens are installed through the opening in the middle of the arched light source, and the arched light source is used to ensure that the image of the cable surface information is obvious.

[0011] The defect detection unit includes an industrial control computer, a display, and an alarm. The industrial control computer is connected to the image acquisition unit, and also connected to the display and the alarm. The industrial control computer is responsible for analyzing and processing the pictures collected by the image acquisition unit using defect detection algorithms, and the display and the alarm are responsible for outputting the processing results in a predefined manner.

[0012] The overall defect detection device adopts an openable and closable design, and circular holes are reserved on each side for the cable to pass through, ensuring that the defect detection device supports online and offline operations at any time.

[0013] Furthermore, the light-shielding housing is composed of a high-contrast background board inside and is treated to prevent reflection, and its inner surface is an anti-reflection surface.

[0014] Furthermore, the support structure includes a support frame body and a support air rod fixed on the support frame body;

[0015] The lower half of the light-shielding housing is fixed on the support frame body, and the upper half of the light-shielding housing is connected to the support air rod;

[0016] The upper and lower halves of the light-shielding housing are connected by a rotating shaft and a hinge at the connection of one side to achieve upper and lower opening and closing.

[0017] The overall light-shielding housing adopts an openable and closable design, and the opening and closing can be achieved by manual opening and closing + air rod, ensuring labor-saving opening and closing and maintaining the open cover state.

[0018] Furthermore, semi-circular holes are respectively opened on both side walls of the upper and lower halves of the light-shielding housing. When the upper and lower halves are closed, the semi-circular holes respectively opened on the upper and lower halves combine to form the cable through-hole.

[0019] Circular holes are reserved on each side of the light-shielding housing, which can ensure that the device supports online and offline operations at any time. The opening size should be set appropriately to ensure that the cable is not scratched.

[0020] Furthermore, universal wheels and adjustable support feet are installed at the bottom of the support structure, which is convenient for front and back movement and fixation. When moving, raise the adjustable support feet and move through the universal wheels; when fixation is required, lower the adjustable support feet to lift the universal wheels to achieve fixation.

[0021] Furthermore, a white high-contrast background board is arranged at the position opposite to the point light source inside the light-shielding housing, which is used to make the raised copper wire image with high contrast and can clearly show the broken wire of the raised part.

[0022] Furthermore, the arched light source and the point light source are arranged in a counter-positioned manner to avoid mutual interference between the two sets of light sources.

[0023] Furthermore, in the image acquisition unit, the industrial camera is fixed by adjusting long holes and bolts, and the camera can be moved forward and backward by loosening and tightening the bolts to adapt to different production lines and wire diameters.

[0024] Furthermore, the industrial computer is installed at the lower part of the supporting structure; the defect detection algorithm and program are deployed in the industrial computer;

[0025] A cooling fan assembly is also installed at the bottom of the support structure to dissipate heat for the industrial computer.

[0026] Furthermore, the display is fixedly mounted on one end of the top of the light shielding housing by a fixing rod;

[0027] The alarm is fixed on the top of the light shielding housing at one end away from the display.

[0028] 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.

[0029] Compared with the prior art, the cable cage twisting process defect detection device based on artificial intelligence machine vision of the present invention has the following beneficial effects:

[0030] 1. The device adopts an opening and closing design, which supports the cable quality detection equipment to be put on and taken off at any time, which is convenient for users to use.

[0031] 2. The device uses a point light source and an arch light source to ensure uniform lighting of the cable when it passes through the image acquisition unit and clear imaging of the cable surface information.

[0032] 3. 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.

[0033] 4. A white background board can ensure high contrast to show the wire ridges. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic diagram of the overall structure of a cable cage twisting process defect detection device based on artificial intelligence machine vision provided by an example of the present invention;

[0035] Figure 2 This is a schematic diagram of the internal structure of the light-shielding housing provided in this example of the present invention.

[0036] In the figure: 1. Light-shielding housing, 11. Upper half, 12. Lower half; 21. Point light source, 22. Arch-shaped light source; 31. Display, 32. Alarm, 33. Industrial control computer; 4. Support structure, 41. Universal wheel, 42. Adjustable support foot, 43. Support air rod, 44. Wire diameter gauge; 5. Cable. Detailed implementation manners

[0037] The present invention will be further described below in conjunction with specific embodiments.

[0038] An embodiment of the present invention provides a defect detection device for a cable cage twisting process based on artificial intelligence machine vision, including a light-shielding housing 1, an image acquisition unit 2, a defect detection unit 3, and a support structure 4.

[0039] As Figure 1 shown, the light-shielding housing 1 is an upper and lower opening and closing structure, including an upper half 11 and a lower half 12. The upper half 11 and the lower half 12 of the light-shielding housing 1 are connected by a rotating shaft and a hinge provided at a side connection to achieve upper and lower opening and closing, which is convenient for the device to get on and off the line at any time. The inside of the light-shielding housing 1 is treated with anti-reflection, and an industrial camera and a fixed light source are mainly arranged inside.

[0040] The support structure 4 includes a support frame body and a support air rod 43 fixed on the support frame body. The lower half 12 of the light-shielding housing 1 is fixed on the support frame body, and the upper half 11 of the light-shielding housing 1 is connected to the support air rod 43 to ensure labor-saving opening and closing and maintaining the open state by the support air rod 43.

[0041] The overall light-shielding housing 1 adopts an opening and closing design, and the opening and closing can adopt the method of manual opening and closing + air rod to ensure labor-saving opening and closing and can maintain the open state.

[0042] Semicircular holes are respectively opened on both side walls of the upper half 11 and the lower half 12 of the light-shielding housing 1. When the upper half 11 and the lower half 12 are closed, the semicircular holes respectively opened on the upper half 11 and the lower half 12 form the cable through hole. Round holes are reserved on the side of the light-shielding housing 1, which can ensure that the device supports getting on and off the line at any time. The opening size should be set appropriately to ensure that the cable 5 is not scratched.

[0043] The image acquisition unit 2 is arranged inside the light-shielding housing 1, and the image acquisition unit 2 is mainly composed of two sets of light sources and cameras. The image acquisition unit 2 includes an industrial camera, a lens, and a light source. The light source is mainly composed of two sets of light sources and cameras, including a particle light source camera and an arch-shaped light source camera. The specific arrangement is as follows:

[0044] A set of point light sources 21 arranged above the cable 5, as Figure 2As shown, the point light source 21 is fixed in the upper part 11 of the light shielding housing 1. The point light source 21 is fixed in the upper part 11 of the light shielding housing 1 by adjusting the long hole and the bolt, and the front-back and up-down position can be adjusted. A hole is opened in the middle of the point light source 21 to install an industrial camera and a lens. The main function of the point light source 21 is to ensure uniform lighting of the cable 5 during the process of passing through the image acquisition unit;

[0045] The arched light source arranged on the lower side of the cable 5, such as Figure 1 , Figure 2 As shown, it includes an arched light source 22, which is fixed in the lower half 12 of the light shielding housing 1 through an adjustment slot and bolts, and can be adjusted in front and back positions. The middle of the arched light source 22 is provided with holes for installing industrial cameras and lenses. The main function of the arched light source is to ensure that the cable surface information is clearly imaged.

[0046] In the image acquisition unit, industrial cameras are fixed with adjustable long holes and bolts. The camera can be moved back and forth by loosening and tightening the bolts to adapt to different production lines and line diameters.

[0047] The arch light source and the point light source are arranged in counterposition to avoid mutual interference between the two sets of light sources.

[0048] The shading housing 1 is a housing with an anti-reflective treatment inside, and the inside is mainly composed of a high-contrast background board. A white high-contrast background board is arranged inside the shading housing 1 and at the position opposite to the point light source, so that the raised copper wire can be imaged with high contrast and the raised broken wire can be clearly displayed.

[0049] The defect detection unit 3 includes a display 31, an alarm 32 and an industrial computer 33. The industrial computer 3 is connected to the image acquisition unit 2, and is connected to the display 31 and the alarm 32. The industrial computer 3 is responsible for analyzing and processing the images collected by the image acquisition unit using the defect detection algorithm, and the display 31 and the alarm 32 are responsible for outputting the processing results in a predefined manner.

[0050] The display 31 is fixedly mounted on the top of the right side of the upper half 11 of the light shielding housing 1 through a fixing rod; the alarm 32 is fixed on the top of the left side of the upper half 11 of the light shielding housing 1. The industrial computer 3 is installed at the lower part of the support frame. The defect detection algorithm and program are deployed in the industrial computer 3; the display 31 and the alarm 32 output the defect detection results in a predefined form, including outputting the recognition results in the form of graphics, text and sound.

[0051] A cooling fan assembly is also installed at the bottom of the support structure 4 for ventilation and heat dissipation of the industrial computer 3. Four universal wheels 41 and four adjustable support feet 42 are installed at the bottom of the support structure 4 for easy forward and backward movement and fixation. When fixation is required, the adjustable support feet 42 are lowered to lift the four universal wheels 41 to achieve fixation.

[0052] The overall defect detection device adopts an openable and closable design, and the cable through-hole reserved on its side facilitates the passing of cables, ensuring that the defect detection device supports online and offline operations at any time.

[0053] Through the above specific implementation manners, those skilled in the technical field can easily implement the present invention. However, it should be understood that the present invention is not limited to the above specific implementation manners. Based on the disclosed implementation manners, those skilled in the technical field can arbitrarily combine different technical features to implement different technical solutions.

[0054] Except for the technical features described in the specification, they are all well-known technologies to those skilled in the art.

Claims

1. A wire and cable cage stranding process defect detection device based on artificial intelligence machine vision, characterized in that, It includes a light-shielding shell, an image acquisition unit, a defect detection unit and a supporting structure. The light shielding shell is an upper and lower opening and closing structure, which is fixed and opened and closed by a supporting structure; an image acquisition unit is arranged inside the light shielding shell, and a cable through hole is opened on the light shielding shell; The image acquisition unit includes an industrial camera, a lens and a light source; the light source includes: A point light source is arranged above the cable, and is used to ensure uniform lighting of the cable when it passes through the image acquisition unit; The arched light source is arranged under the cable. The middle opening of the arched light source is used to install the industrial camera and lens. The arched light source is used to ensure that the cable surface information is clearly imaged. The defect detection unit includes an industrial computer, a display and an alarm. The industrial computer is connected to the image acquisition unit, and is connected to the display and the alarm.

2. The wire cage stranding process defect detection device based on artificial intelligence machine vision according to claim 1, wherein, The interior of the light-shielding housing is composed of a high-contrast background plate and is anti-reflective treated, and the inner surface of the housing is an anti-reflective surface.

3. The cable cage stranding process defect detection device based on artificial intelligence machine vision according to claim 1, characterized in that, The support structure includes a support frame and a support gas rod fixed on the support frame; The lower half of the light-shielding shell is fixed on the supporting frame, and the upper half of the light-shielding shell is connected to the supporting gas rod; The upper and lower parts of the light shielding shell are connected by a rotating shaft and a hinge arranged at a side edge connection to achieve upward and downward opening and closing.

4. The defect detection device for the wire and cable cage stranding process based on artificial intelligence machine vision according to claim 1 or 3, characterized in that, Semicircular holes are respectively provided on the two side walls of the upper and lower parts of the light-shielding shell. When the upper and lower parts are closed, the semicircular holes respectively provided in the upper and lower parts are combined to form the cable through hole, so as to support the device to be online and offline at any time.

5. The wire and cable cage stranding process defect detection device based on artificial intelligence machine vision according to claim 1 or 3, characterized in that, The bottom of the support structure is equipped with universal wheels and adjustable support feet. When moving, the adjustable support feet are raised and moved through the universal wheels; when fixing is required, the adjustable support feet are lowered and the universal wheels are raised to achieve fixing.

6. The wire cage stranding process defect detection device based on artificial intelligence machine vision according to claim 1, characterized in that, A white high-contrast background plate is arranged inside the light-shielding shell and at a position opposite to the point light source, so as to image the raised copper wire with high contrast.

7. An apparatus for detecting defects in the cable cage stranding process based on artificial intelligence machine vision according to claim 1, characterized in that, The arched light source and the point light source are arranged in a counterposition manner to avoid mutual interference between the two sets of light sources.

8. An apparatus for detecting process defects of a cable cage stranding based on artificial intelligence machine vision according to claim 1, wherein, In the image acquisition unit, the industrial camera is fixed by adjusting long holes and bolts, and the camera can be moved forward and backward by loosening and tightening the bolts to adapt to different production lines and wire diameters.

9. The wire and cable cage stranding process defect detection device based on artificial intelligence machine vision according to claim 1 or 3, characterized in that The industrial computer is installed at the lower part of the supporting structure; the defect detection algorithm and program are deployed in the industrial computer; A cooling fan assembly is also installed at the bottom of the support structure to dissipate heat for the industrial computer.

10. The defect detection device for the wire and cable cage stranding process based on artificial intelligence machine vision according to claim 1, wherein, The display is fixedly mounted on one end of the top of the light shielding housing through a fixing rod; the alarm is fixed on one end of the top of the light shielding housing away from the display; 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