Circuit board automatic optical detection device based on AI defect identification

Abstract

A circuit board automatic optical detection device based on AI defect identification comprises a machine body, and a conveying device, a detection device, a manipulator, a main control device and a temporary storage device which are arranged in the machine body, and the main control device is connected to the conveying device, the detection device, the manipulator and the temporary storage device; the conveying device comprises a feeding conveying device and a discharging conveying device; a detection position is arranged in the machine body, the feeding conveying device transfers a circuit board to the detection position in the machine body, and the detection device carries out defect identification detection on the circuit board; the mechanical arm sorts the circuit boards to the discharging conveying device or the temporary storage device according to the detected result. The master control device comprises an in-inspection display screen and a reinspection display screen. The detection device provided by the utility model can realize on-line redetection without shutdown or speed reduction during rapid detection. The working efficiency is improved, and the recheck storage pressure of abnormal products is reduced; the device is high in practicability and has high popularization significance.

Description

Technical Field

[0001] This utility model relates to the field of circuit board inspection technology; and in particular to an automatic optical inspection device for circuit boards based on AI defect recognition. Background Technology

[0002] As electronic products move towards higher density and miniaturization, the manufacturing process of printed circuit boards (PCBs) has become significantly more complex. The accuracy and efficiency of detecting surface defects (such as short circuits, open circuits, poor solder joints, foreign matter residue, and copper foil scratches) directly affect product yield and reliability. Traditional manual visual inspection is limited by high subjectivity, low efficiency, and fatigue, and can no longer meet the demands of modern electronics manufacturing for high-speed, high-precision inspection. Currently, most mainstream automated optical inspection equipment uses rule-based algorithms or template matching technology to achieve automated inspection, which greatly improves work efficiency. However, current automated inspection still has a certain possibility of false detection, and manual re-inspection is still necessary to ensure accuracy. When an anomaly is detected, staff re-inspect the defective area online according to the indicated defective area. However, when the inspection speed is high and the defect rate is high, it is necessary to pause or slow down to provide sufficient re-inspection time, thus affecting inspection efficiency. In addition, to improve efficiency, some equipment uses automation to sort defective products to a defective product area, where staff then transfer them to a defective product processing area for unified processing. However, this method cannot promptly re-inspect anomalies detected on the equipment, increasing the difficulty of re-inspection and reducing the timeliness of re-inspection processing. If a misjudgment is not detected in time, multiple misjudgments of the same type may occur subsequently. Utility Model Content

[0003] Therefore, it is necessary to provide an automated optical inspection device for circuit boards based on AI defect recognition to address the shortcomings of existing technologies.

[0004] An automated optical inspection device for circuit boards based on AI defect recognition includes a main body and a conveying device, a detection device, a robotic arm, a main control device, and a temporary storage device disposed within the main body. The main control device is connected to the conveying device, the detection device, the robotic arm, and the temporary storage device. The conveying device includes an infeed conveying device and an outfeed conveying device. A detection position is provided within the main body. The infeed conveying device transfers the circuit board to the detection position within the main body, and the detection device performs defect recognition and detection on the circuit board. The robotic arm sorts the circuit boards to the outfeed conveying device or the temporary storage device based on the detection results. The main control device includes an inspection display screen and a re-inspection display screen.

[0005] Furthermore, the detection device includes a camera module, an image processing module, an analysis and comparison module, and an alarm module; the camera module is located directly above the detection position, the image processing module and the analysis and comparison module are both located inside the main control device, and the alarm module is located on the top of the machine body.

[0006] Furthermore, the camera module includes a camera and several fill lights, which are evenly distributed around the camera and all emit light toward the circuit board of the detection position.

[0007] Furthermore, the temporary storage device is located below and in front of the detection position, and the temporary storage device includes multiple layers of temporary storage in upper and lower rows.

[0008] Furthermore, the temporary storage device includes temporary storage racks arranged side by side at intervals, and the temporary storage racks are provided with support plates arranged side by side vertically, with the support plates at corresponding positions of the two temporary storage racks being arranged horizontally.

[0009] Furthermore, the temporary storage rack includes two side plates, two rotating chains, two rotating shafts, and a support plate. The two side plates are arranged in a front-to-back orientation, and the two rotating shafts are arranged vertically on the inner sides of the two side plates. The two rotating chains are respectively vertically installed at the corresponding side ends of the two rotating shafts, and the two ends of the support plate are installed at the corresponding positions of the two chains.

[0010] Furthermore, the bottom of the temporary storage device is provided with two guide rails, and the two temporary storage racks are mounted on the guide rails and move along the guide rails to move away from or towards each other.

[0011] Furthermore, it also includes a sensor, which is mounted on a support plate and whose information is connected to the main control device.

[0012] Furthermore, it also includes a scanner connected to the re-inspection display screen.

[0013] In summary, this invention provides an automated optical inspection device for circuit boards based on AI defect recognition. By incorporating a temporary storage device and a re-inspection display screen, the device enables online re-inspection during rapid testing without requiring shutdown or speed reduction. This improves work efficiency and reduces the pressure of storing defective products for re-inspection. This invention is highly practical and has significant potential for widespread application. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of the first embodiment of the automatic optical inspection device for circuit boards based on AI defect recognition of this utility model.

[0015] Figure 2 for Figure 1 Schematic diagram of the internal structure of the detection device;

[0016] Figure 3 for Figure 2 A side view of the temporary storage device;

[0017] Figure 4 This is a schematic diagram of the camera device.

[0018] Figure 5 This is a schematic diagram of the structure of the second embodiment of the present utility model. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this utility model clearer, the present utility model will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this utility model and are not intended to limit this utility model.

[0020] like Figures 1 to 4 As shown, this utility model provides an automatic optical inspection device for circuit boards based on AI defect recognition. The device includes a main body 10 and a conveying device 10, a detection device, a robotic arm (not shown), a main control device, and a temporary storage device 50, all housed within the main body 10. The conveying device 10 includes an infeed conveying device 11 and an outfeed conveying device 12. A detection position 13 is provided within the main body 10. The infeed conveying device 11 transfers the circuit boards to the detection position 13 within the main body 10. The detection device performs defect recognition and detection on the circuit boards 100. The robotic arm sorts the circuit boards 100 according to the detection results. If they are good products, the robotic arm transfers them to the outfeed conveying device 12 for transport to the next process. If they are defective products, they are transferred to the temporary storage device 50 for temporary storage, re-inspection, or rework.

[0021] The detection device includes a camera module 20, an image processing module, an analysis and comparison module, and an alarm module 21. The camera module 20 is positioned directly above the detection position 13. The image processing module and the analysis and comparison module are both located within the main control device, and the alarm module 21 is located on the top of the main body 10. The main control device has a control panel 22, through which the image information and analysis and comparison information detected by the detection device are displayed and stored. When an anomaly is detected, the main control device transmits a signal to the alarm device to issue an alarm. The camera module 20 includes a camera 201 and supplementary lights 202. In this embodiment, four supplementary lights 202 are provided around the camera 201 to illuminate the circuit board from all angles, thereby improving the clarity of the image. The image processing module processes the image to make it clearer for comparison. The analysis and comparison module compares and analyzes the processed image with a standard image. The alarm module 21 issues an alarm when an anomaly is detected.

[0022] The temporary storage device 50 is located below and in front of the detection position 13. The temporary storage device 50 includes temporary storage racks 51 arranged side-by-side at intervals. Two guide rails 40 are provided at the bottom of the temporary storage device 50, and the two temporary storage racks 51 are mounted on the guide rails 40 and can move along the guide rails 40 to move away from or towards each other; thus, it can be used to support and limit the movement of plates of various sizes. Each temporary storage rack 51 includes two side plates 511, two rotating chains 512, two rotating shafts 513, a support plate 514, and a sensor. The two side plates 511 are arranged front-to-back facing each other. The two rotating shafts 513 are arranged vertically on the inner sides of the side plates 511. The two rotating chains 512 are vertically mounted on the corresponding ends of the two rotating shafts 513, and the rotating chains 512 rotate around the two rotating shafts 513. The two ends of the support plate 514 are mounted on the corresponding positions of the two chains, and the synchronous rotation of the two chains can move the support plate 514 up and down. The sensor is mounted on the support plate 514. When a circuit board falls onto the support plate 514, the sensor detects the information of the board and the rotating chain 512 rotates downwards by one step to facilitate the reception of the next circuit board. Conversely, when both the upper and lower support plates 514 are occupied by circuit boards, and the topmost circuit board is removed, the support plate 514 will rise.

[0023] During operation, circuit boards enter the machine body 10 via the feeding conveyor 11. A robotic arm transfers the circuit boards to the detection position 13, where the detection device performs the inspection. If the product is good, the robotic arm transfers it to the discharge conveyor 12 for the next process. If the detected product is defective, the robotic arm transfers it to the two uppermost support plates 514 of the temporary storage device 50. Sensors on the support plates 514 detect the board information and associate it with the board's abnormal information. Then, the robotic arm continues to move new circuit boards to the detection position 13 for inspection. The control panel 22 includes a detection display screen and a re-inspection display screen. The detection display screen shows the inspected product information, while the re-inspection display screen shows the re-inspected product information. When a worker removes a circuit board, the re-inspection display screen shows the abnormal information detected on that layer of the circuit board, allowing the worker to re-inspect the corresponding abnormal information points; this is more timely and clear, and eliminates the need for equipment pauses or speed reductions.

[0024] like Figure 5 As shown, this is the second embodiment of the present invention. The structure of this embodiment is basically the same as that of the first embodiment, except that the re-inspection display screen in this embodiment is an independent computer screen 221, which also includes a scanner (not shown). When the circuit board is provided with a corresponding traceable QR code, the carrier plate 514 does not need to be equipped with a sensor. The QR code information can be read directly by the scanning device, and the abnormal points can be viewed on the re-inspection display screen, thereby facilitating the re-inspection of the corresponding abnormal points.

[0025] In summary, this utility model's automatic optical inspection device for circuit boards based on AI defect recognition, by incorporating a temporary storage device 50 and a re-inspection display screen, enables online re-inspection during rapid testing without stopping or slowing down. This improves work efficiency and reduces the pressure of re-inspecting and storing defective products. This utility model is highly practical and has significant potential for widespread application.

[0026] The above-described embodiments only illustrate two implementation methods of this utility model, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of this utility model patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this utility model, and these all fall within the protection scope of this utility model. Therefore, the protection scope of this utility model patent should be determined by the appended claims.

Claims

1. An automated optical inspection device for circuit boards based on AI defect recognition, characterized in that: The system includes a main body and a conveying device, a detection device, a robotic arm, a main control device, and a temporary storage device disposed within the main body. The main control device is connected to the conveying device, the detection device, the robotic arm, and the temporary storage device. The conveying device includes an infeed conveying device and an outfeed conveying device. A detection position is provided within the main body. The infeed conveying device transfers circuit boards to the detection position within the main body, and the detection device performs defect identification and detection on the circuit boards. The robotic arm sorts the circuit boards to the outfeed conveying device or the temporary storage device based on the detection results. The main control device includes an inspection display screen and a re-inspection display screen.

2. The automated optical inspection device for circuit boards based on AI defect recognition as described in claim 1, characterized in that: The detection device includes a camera module, an image processing module, an analysis and comparison module, and an alarm module; the camera module is located directly above the detection position, the image processing module and the analysis and comparison module are both located inside the main control device, and the alarm module is located on the top of the machine body.

3. The automatic optical inspection device for circuit boards based on AI defect recognition as described in claim 2, characterized in that: The camera module includes a camera and several fill lights, which are evenly distributed around the camera and all emit light toward the circuit board of the detection position.

4. The automatic optical inspection device for circuit boards based on AI defect recognition as described in claim 1, characterized in that: The temporary storage device is located below and in front of the detection position, and the temporary storage device includes multiple layers of temporary storage.

5. The automatic optical inspection device for circuit boards based on AI defect recognition as described in claim 4, characterized in that: The temporary storage device includes temporary storage racks arranged side by side at intervals, and the temporary storage racks are provided with support plates arranged side by side vertically, with the support plates at corresponding positions of the two temporary storage racks being arranged horizontally.

6. The automatic optical inspection device for circuit boards based on AI defect recognition as described in claim 5, characterized in that: The temporary storage rack includes two side plates, two rotating chains, two rotating shafts, and a support plate. The two side plates are arranged in a front-to-back orientation, and the two rotating shafts are arranged vertically on the inner sides of the two side plates. The two rotating chains are respectively vertically installed on the corresponding side ends of the two rotating shafts, and the two ends of the support plate are installed on the corresponding positions of the two chains.

7. The automatic optical inspection device for circuit boards based on AI defect recognition as described in claim 4, characterized in that: The bottom of the temporary storage device is provided with two guide rails, and the two temporary storage racks are mounted on the guide rails and move along the guide rails to move away from or towards each other.

8. The automated optical inspection device for circuit boards based on AI defect recognition as described in claim 1, characterized in that: It also includes a sensor, which is mounted on a support plate and whose information is connected to the main control device.

9. The automated optical inspection device for circuit boards based on AI defect recognition as described in claim 1, characterized in that: It also includes a scanner, which is connected to the re-inspection display screen.

Images