Detection device for metal strip

Abstract

The utility model discloses a metal strip detection device which comprises a first support and a second support which are arranged on one side of a detection channel in a spaced mode, and a second camera and a first camera are arranged on the first support and the second support respectively. The second camera and the first camera are arranged on the upper side and the lower side of the detection channel respectively and face the detection channel. The metal strip is arranged on the detection channel, the upper side and the lower side of the metal strip are photographed and detected through the first camera and the second camera on the upper side and the lower side respectively, surface detection is conducted on the upper face and the lower face of the metal strip, and the detection efficiency is improved.

Description

Technical Field

[0001] This utility model relates to the technical field, specifically to a detection device for metal strips. Background Technology

[0002] Metal strips include copper alloy strips, copper strips, and aluminum strips. Copper alloy strips, as lead frames in the manufacture of integrated circuits, play a role in supporting chips, protecting internal components, connecting external circuits, dissipating heat from components, and conducting electricity. In terms of specifications, they are required to be short, small, light, and thin, while also having extremely high surface quality requirements. Surface defects such as pits, scratches, oxidation, and peeling are not allowed. Therefore, online surface quality inspection during the production process of copper alloy strips is particularly important.

[0003] Metal strip is typically inspected manually, which is time-consuming, labor-intensive, and inefficient. Another method uses a camera to photograph the metal strip and performs image recognition for inspection. However, this method cannot inspect both sides of the metal strip simultaneously, resulting in low efficiency. Utility Model Content

[0004] In view of the above-mentioned technical problems existing in the prior art, the present invention provides a metal strip detection device that can continuously perform surface detection on both sides of the metal strip.

[0005] This utility model discloses a metal strip detection device, including a first support and a second support spaced apart on one side of a detection channel. A second camera and a first camera are respectively installed on the first support and the second support. The second camera and the first camera are respectively installed on the upper and lower sides of the detection channel and face the detection channel.

[0006] Preferably, lights are provided on one side of the first camera and the second camera.

[0007] Preferably, the lower side of the first bracket is provided with a first mounting base and a second mounting base, and the first camera and the first light are respectively mounted on the first mounting base and the second mounting base; the upper side of the second bracket is provided with a third mounting base and a fourth mounting base, and the second camera and the second light are respectively mounted on the third mounting base and the fourth mounting base.

[0008] Preferably, rollers are provided on the upper and / or lower sides of the detection channel; the detection channel is located on one side of the rollers.

[0009] Preferably, the roller includes a first roller and a second roller respectively disposed on both sides of the detection channel, the first roller being mounted on a first support and the second roller being mounted on a second support.

[0010] Preferably, it also includes a slitting machine and a first conveyor belt, wherein the output end of the slitting machine is connected to the detection channel via the first conveyor belt.

[0011] Preferably, the output end of the detection channel is connected to the second transmission belt.

[0012] Preferably, the slitting machine is a longitudinal slitting machine.

[0013] Preferably, it also includes a detection host and a display, wherein the detection host is connected to the display, the first camera and the second camera respectively.

[0014] Compared with the prior art, the beneficial effects of this utility model are as follows: the metal strip is set on the detection channel, and the first and second cameras on the upper and lower sides of the metal strip are photographed and detected respectively, and the surface of the upper and lower surfaces of the metal strip is detected, thereby improving the detection efficiency. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the structure of the metal strip inspection device of this utility model;

[0016] Figure 2 This is a logic block diagram of the detection device of this utility model;

[0017] Figure 3 This is a schematic diagram of the first roller.

[0018] The diagram shows: 1. Detection device; 11. Detection channel.

[0019] 2 First bracket, 21 First roller, 22 First mounting base, 23 First camera, 25 Second mounting base, 26 First light,

[0020] 3 Second support, 31 Second roller, 32 Third mounting base, 33 Second camera, 35 Fourth mounting base, 36 Second light, 5 Metal strip, 51 Slitting, 6 Slitting machine, 61 First conveyor belt, 63 Second conveyor belt, 7 Detection host, 8 Display. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of this utility model clearer, the technical solutions of the embodiments of this utility model will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this utility model. Based on the embodiments of this utility model, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of this utility model.

[0022] The present invention will now be described in further detail with reference to the accompanying drawings:

[0023] A metal strip detection device 1, such as Figure 1 As shown, it includes a first bracket 2 and a second bracket 3 spaced apart on one side of the detection channel 11. A second camera 33 and a first camera 23 are respectively mounted on the first bracket 2 and the second bracket 3. The second camera 33 and the first camera 23 are respectively mounted on the upper and lower sides of the detection channel 11 and face the detection channel 11.

[0024] The metal strip 5 is placed on the detection channel 11. The first camera 23 and the second camera 33 on the upper and lower sides of the metal strip take pictures and detect the upper and lower sides of the metal strip respectively, and perform surface detection on the upper and lower surfaces of the metal strip to improve detection efficiency.

[0025] The first camera 23 and the second camera 33 are each equipped with a light on one side to provide illumination for the cameras. More specifically, the lower side of the first bracket 2 is provided with a first mounting base 22 and a second mounting base 25, and the first camera 23 and the first light 26 are respectively mounted on the first mounting base 22 and the second mounting base 25; the upper side of the second bracket 3 is provided with a third mounting base 32 and a fourth mounting base 35, and the second camera 33 and the second light 36 are respectively mounted on the third mounting base 32 and the fourth mounting base 35.

[0026] Rollers are provided on the upper and / or lower sides of the detection channel 11; the detection channel 11 is located on one side of the rollers. The rollers are used to drive the metal strip 5 to be transported on the detection channel 11, which can realize online detection of the metal strip.

[0027] More specifically, the rollers include a first roller 21 and a second roller 31 respectively disposed on both sides of the detection channel 11. The first roller 21 is mounted on the first support 2 and the second roller 31 is mounted on the second support 3 to achieve advantageous metal strip transport. Figure 3 The structure of the first roller 21 is shown; the second roller 31 can adopt the same structure.

[0028] It should be noted that holes or slots leading to the metal strip are provided on the upper and lower sides of the detection channel 11, so that the camera can capture images or videos of the metal strip without obstruction or occlusion.

[0029] like Figure 2 This utility model also includes a slitting machine 6 and a first conveyor belt 61. The output end of the slitting machine 6 is connected to the detection channel 11 through the first conveyor belt 61. The slitting machine 6 is used to slit the metal strip into multiple strips 51, and the surface of the strips 51 can be detected by a camera.

[0030] Optionally, a second conveyor belt 63 is provided at the output end of the detection channel 11. The slitting machine 6 can be a longitudinal slitting machine. Specifically, copper alloy strip with a width of 350-450mm and a thickness of 0.1-1.0mm is slited by the longitudinal slitting machine into strips with a width of 20-100mm and a total number of strips of 4-24. More specifically, copper alloy strip with a width of 450mm and a thickness of 1.0mm is slid by the longitudinal slitting machine into strips with widths of 7 strips of 20mm, 2 strips of 30mm, 2 strips of 100mm, and 1 strip of 50mm, for a total of 12 strips.

[0031] Figure 2 The detection host 7 and the display 8 were also determined. The detection host 7 is connected to the display 8, the first camera 23, and the second camera 33, respectively. The detection host 7 is used to control the first camera 23 and the second camera 33, and to receive the images uploaded by them, and to detect defects in the metal strip based on the images.

[0032] Preferably, the detection host is a machine learning-based detection host. In a specific detection process, the detection steps of the detection host are: edge extraction and detection area determination → defect localization → defect feature combination and classification → outputting defect classification results / detection completion.

[0033] The current edge position is located by an adaptive edge localization algorithm. A corresponding number of detection boxes are placed at the material edge. The boundary between the copper strip (bright) and the gap (dark) is determined by a high-precision first-order derivative edge algorithm. Interference is filtered by a filtering algorithm. The boundary between the substrate and the gap is searched. The edge is fitted by an interpolation algorithm. Each detection item is calculated by edge calculation, supporting the detection of multiple strips.

[0034] More specifically, the inspection host uses a deep learning model (such as a convolutional neural network) as a feature extractor, inputting the copper strip image into the network. Low-level features of the image, such as edges and textures, are extracted at lower levels of the network. High-level semantic features of the image, such as shape and texture patterns, are extracted at higher levels of the network. Through training the deep learning model, the learned features can better represent defect information in the copper foil image. After detecting defects and their classification results, the inspection host can output an inspection report via a monitor or printer.

[0035] The above are merely preferred embodiments of this utility model and are not intended to limit the scope of this utility model. Various modifications and variations can be made to this utility model by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this utility model should be included within the protection scope of this utility model.

Claims

1. A detection device for metal strip, characterized in that, Includes a first bracket (2) and a second bracket (3) spaced apart on one side of the detection channel (11), The first bracket (2) and the second bracket (3) are respectively equipped with a second camera (33) and a first camera (23); The second camera (33) and the first camera (23) are respectively set on the upper and lower sides of the detection channel (11) and face the detection channel (11).

2. The detection device according to claim 1, characterized in that, Lights are provided on one side of the first camera (23) and the second camera (33).

3. The detection device according to claim 2, characterized in that, The first bracket (2) is provided with a first mounting base (22) and a second mounting base (25) on its lower side. The first camera (23) and the first light (26) are respectively mounted on the first mounting base (22) and the second mounting base (25). The second bracket (3) is provided with a third mounting base (32) and a fourth mounting base (35) on its upper side, and the second camera (33) and the second light (36) are respectively mounted on the third mounting base (32) and the fourth mounting base (35).

4. The detection device according to claim 1, characterized in that, Rollers are provided on the upper and / or lower sides of the detection channel (11); The detection channel (11) is located on one side of the roller.

5. The detection device according to claim 4, characterized in that, The rollers include a first roller (21) and a second roller (31) respectively disposed on both sides of the detection channel (11). The first roller (21) is mounted on the first support (2), and the second roller (31) is mounted on the second support (3).

6. The detection device according to claim 1, characterized in that, It also includes a slitting machine (6) and a first conveyor belt (61), The output end of the slitting machine (6) is connected to the detection channel (11) via the first transmission belt (61).

7. The detection device according to claim 6, characterized in that, The output end of the detection channel (11) is connected to the second transmission belt (63).

8. The detection device according to claim 6, characterized in that, The slitting machine (6) is a longitudinal slitting machine.

9. The detection device according to claim 1, characterized in that, It also includes a detection host (7) and a display (8), wherein the detection host (7) is connected to the display (8), the first camera (23) and the second camera (33) respectively.

Images