Industrial vision online defect detection AIoT early warning device

Abstract

The utility model discloses an industrial vision online defect detection AIoT early warning device, which comprises a casing and a main control board arranged in the casing, and further comprises a shadowless lamp, a CCD (Charge Coupled Device) camera module, an NG (Natural Gas) marking device and a sound-light alarm module. The shadowless lamp is arranged on the first face of the machine shell, the light emitting direction of the shadowless lamp faces the flow conveying line, and the shadowless lamp is connected with the main control board. The CCD camera module is installed on the first side face of the machine shell and connected with the main control board. The NG marking device is installed on the first side face of the machine shell and connected with the main control board. The sound-light alarm module is installed on the machine shell and connected with the main control board. According to the industrial visual online defect detection AIoT early warning device disclosed by the utility model, when defective products are detected to appear on a plurality of continuously passing targets, early warning can be carried out in time, so that loss is stopped in time, and a large number of defective products are prevented from being caused. The industrial visual on-line defect detection AIoT early warning device disclosed by the utility model is easy to install.

Description

Technical Field

[0001] The utility model relates to a visual inspection system, specifically to an industrial visual online defect detection AIoT early warning device. Background Art

[0002] AIoT (Artificial Intelligence Internet of Things) = AI (Artificial Intelligence) + IoT (Internet of Things). AIoT integrates AI technology and IoT technology, generates and collects massive amounts of data from different dimensions through the Internet of Things and stores them in the cloud and edge. Then, through big data analysis and higher forms of artificial intelligence, it realizes the digitization and intelligent connection of all things.

[0003] Efficient and reliable automatic inspection is an important part of the automation of the electronics manufacturing industry. As the size of components used in the production of electronic products becomes smaller and smaller, and the assembly integration density becomes higher and higher, it is more necessary for automatic machine vision inspection (AVI or AOI) to replace traditional manual visual inspection. At present, the length and width of the smallest O1005 patch component are only 0.1x0.2mm, and the pin spacing of the fine device is only 0.1mm. The main production links of the surface mount installation production line of printed circuit boards include board installation, solder paste printing, chip shooting, IC chip placement, reflow soldering fixation, perforated component assembly, wave soldering, packaging, etc. Among them, more than 80% of the quality defects of electronic products produced by patch production are caused by solder paste printing defects. However, the quality inspection technology of solder paste printing is difficult, not only involving two-dimensional images, but also requiring accurate three-dimensional reconstruction to detect volume and three-dimensional shape. Since the minimum size of electronic devices has reached 0.1mm, the horizontal resolution of the machine vision inspection of solder paste printing quality is required to reach 10μm level, and the third dimension thickness accuracy must reach 1μm. At high resolution, there are problems such as large data volume and slow processing speed. The conflict between speed and accuracy is the biggest difficulty in microstructure 3D inspection, which poses a challenge to traditional machine vision inspection methods.

[0004] In the prior art, the inspection of the surface mount of the printed circuit board is completed by a visual inspection system. However, during the inspection process of the visual inspection system in the prior art, only NG can be determined based on the inspection result, and no warning can be issued. If no warning is issued during mass production, great property losses will be caused.

[0005] Therefore, it is necessary to set up an early warning device to solve such problems. Utility Model Content

[0006] In view of the deficiencies in the prior art, the technical problem to be solved by the utility model is to provide an industrial vision online defect detection AIoT early warning device. The purpose of designing the early warning device is to stop losses in time and avoid producing a large number of defective products.

[0007] In order to solve the above technical problems, the utility model is implemented by the following scheme: An industrial visual online defect detection AIoT early warning device of the utility model includes a housing and a main control board arranged in the housing, and also includes:

[0008] A shadowless lamp is arranged on the first surface of the housing and the light emission direction of the shadowless lamp faces the water conveying line, and the shadowless lamp is connected to the main control board;

[0009] A CCD camera module is mounted on the first side of the housing and connected to the main control board;

[0010] An NG marker, the NG marker being mounted on the first side of the housing and connected to the main control board;

[0011] The sound and light alarm module is installed in the casing and connected to the main control board.

[0012] Furthermore, the shadowless lamp is an LED matrix.

[0013] Furthermore, the angle of the CCD camera module is adjustable.

[0014] Furthermore, the main control board is provided with a wireless network signal module and a wired network edge signal module.

[0015] Furthermore, a signal transceiver antenna is installed on the second side of the housing, and the signal transceiver antenna is connected to the main control board.

[0016] Furthermore, the sound and light alarm module includes at least one speaker for issuing an alarm and an LED red light alarm lamp arranged in the shadowless lamp area.

[0017] Furthermore, a clamping mechanism is installed on the back of the housing.

[0018] Furthermore, the early warning device also includes a fill light, which is installed on the first side of the housing and close to the CCD camera module, and is connected to the main control board.

[0019] Furthermore, the fill light angle is adjustable.

[0020] Compared with the prior art, the beneficial effects of the utility model are:

[0021] 1. When defective products are detected in multiple targets passing continuously, the industrial vision online defect detection AIoT early warning device of the utility model will issue an early warning in time to stop the loss in time and avoid producing a large number of defective products.

[0022] 2. The industrial vision online defect detection AIoT early warning device of the utility model is easy to install.

[0023] 3. The NG marker of the industrial vision online defect detection AIoT early warning device of the utility model can mark the defective products passing through with the NG symbol, and this symbol is easy to clean. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a three-dimensional structural diagram of the utility model's industrial vision online defect detection AIoT early warning device.

[0025] Figure 2 This is a top view of the industrial vision online defect detection AIoT early warning device of the utility model.

[0026] Markings in the accompanying drawings: housing 1, speaker 2, signal transceiver antenna 3, handle 4, CCD camera module 5, fill light 6, NG marker 7, clamping mechanism 8, shadowless lamp 9. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the utility model to clearly and completely describe the technical solutions in the embodiments of the utility model, so that the advantages and features of the utility model can be more easily understood by those skilled in the art, thereby making a clearer and more explicit definition of the protection scope of the utility model. Obviously, the embodiments described in the utility model are only part of the embodiments of the utility model, not all of the embodiments. Based on the embodiments in the utility model, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the utility model.

[0028] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0029] Embodiment 1: The specific structure of the utility model is as follows:

[0030] Please refer to the attached Figure 1-2 The utility model is an industrial visual online defect detection AIoT early warning device, comprising a housing 1 and a main control board arranged in the housing 1. The housing 1 is a square structure, and its third side has multiple interfaces and control buttons, including a power interface, a signal interface, and a network interface. Two handles 4 are arranged on both sides of the first side of the housing 1, and the handles 4 are more convenient for operating the early warning device.

[0031] Industrial vision online defect detection AIoT early warning device also includes:

[0032] A shadowless lamp 9 is arranged on the first surface of the housing 1 and the light direction of the shadowless lamp 9 is toward the water conveying line. The shadowless lamp 9 is connected to the main control board. The shadowless lamp 9 is an LED matrix, which can illuminate the passing patches without blind spots to avoid shadow areas on the patches.

[0033] A CCD camera module 5 is installed on the first side of the housing 1 and connected to the main control board. The camera of the CCD camera module 5 faces the assembly line, and the passing patches pass through the camera area.

[0034] An NG marker 7, which is installed on the first side of the housing 1 and connected to the main control board. When a defective patch is found among the patches passing through, the NG marker 7 marks the defective patch with the word NG.

[0035] The sound and light alarm module is installed in the housing 1 and connected to the main control board. The sound and light alarm module emits a sound alarm and a red light alarm.

[0036] A preferred technical solution of this embodiment: the angle of the CCD camera module 5 is adjustable, and its adjustable structure is that the CCD camera body and the adapter are rotatably connected and fastened with bolts and a butterfly valve to achieve the purpose of angle adjustment.

[0037] A preferred technical solution of this embodiment: the main control board is provided with a wireless network signal module and a wired network edge signal module. The utility model is provided with a wireless network signal module and a wired network edge signal module. When a problem occurs in the wired network edge signal module, the wireless network signal module temporarily replaces the wired network edge signal module to avoid data not being fed back to the background in time. The wireless network signal module adopts a 4G module.

[0038] A preferred technical solution of this embodiment: a signal transceiver antenna 3 is installed on the second side of the housing 1, and the signal transceiver antenna 3 is connected to the main control board.

[0039] A preferred technical solution of this embodiment: the sound and light alarm module includes at least one speaker 2 for sounding an alarm and an LED red light alarm lamp arranged in the area of ​​the shadowless lamp 9. Figure 1 As shown, two speakers 2 are arranged on both sides of the lower front side of the housing 1. After the sound and light alarm module is triggered, the speakers 2 and the LED red light alarm light work simultaneously, the assembly line conveyance stops, and the patch is no longer transmitted to the next processing step.

[0040] A preferred technical solution of this embodiment: a clamping mechanism 8 is also installed on the back of the housing 1. Figure 2 As shown, the clamping mechanism 8 includes a C-shaped clamp seat, a C-shaped clamp cover rotatably connected to the C-shaped clamp seat, a screw hole is provided on the C-shaped clamp seat, a rotating handle is connected to the C-shaped clamp cover, and the rotating handle is connected to a screw. The rotating handle rotates to allow the screw to enter the screw hole. The clamping mechanism 8 of the utility model is similar to the clamping mechanism of a bicycle seat.

[0041] A preferred technical solution of this embodiment: the early warning device also includes a fill light 6, which is installed on the first side of the casing 1 and close to the CCD camera module 5, which is connected to the main control board, and the fill light 6 is used for fill light, and the angle of the fill light 6 is adjustable.

[0042] In summary, when defective products are detected in multiple targets passing continuously, the industrial vision online defect detection AIoT early warning device of the utility model will give a timely early warning to stop losses in time and avoid causing a large number of defective products. The industrial vision online defect detection AIoT early warning device of the utility model is easy to install. The NG marker of the industrial vision online defect detection AIoT early warning device of the utility model can mark the defective products passing by with the NG defective product symbol, and this symbol is easy to clean.

[0043] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An industrial visual online defect detection AIoT early warning device, comprising a housing (1) and a main control board arranged in the housing (1), characterized in that: Also includes: A shadowless lamp (9) is arranged on the first surface of the housing (1) and the light emission direction of the shadowless lamp (9) is toward the water conveying line. The shadowless lamp (9) is connected to the main control board; A CCD camera module (5) is mounted on the first side surface of the housing (1) and is connected to the main control board; An NG marker (7), the NG marker (7) being mounted on a first side surface of the housing (1) and connected to the main control board; An audible and visual alarm module is installed on the housing (1) and connected to the main control board.

2. According to claim 1, an industrial visual online defect detection AIoT early warning device is characterized in that: The shadowless lamp (9) is an LED matrix.

3. According to claim 1, an industrial visual online defect detection AIoT early warning device is characterized in that: The angle of the CCD camera module (5) is adjustable.

4. According to claim 1, an industrial visual online defect detection AIoT early warning device is characterized in that: The main control board is provided with a wireless network signal module and a wired network edge signal module.

5. The industrial visual online defect detection AIoT early warning device according to claim 1 is characterized in that: A signal transceiver antenna (3) is installed on the second side of the housing (1), and the signal transceiver antenna (3) is connected to the main control board.

6. The industrial visual online defect detection AIoT early warning device according to claim 1 is characterized in that: The sound and light alarm module comprises at least one speaker (2) for issuing an alarm and an LED red light alarm lamp arranged in the area of ​​the shadowless lamp (9).

7. The industrial visual online defect detection AIoT early warning device according to claim 1 is characterized in that: A clamping mechanism (8) is also installed on the back of the housing (1).

8. The industrial visual online defect detection AIoT early warning device according to claim 1 is characterized in that: The early warning device also includes a fill light (6), which is installed on the first side of the housing (1) and close to the CCD camera module (5), and is connected to the main control board. The fill light (6) is used for fill light.

9. The industrial visual online defect detection AIoT early warning device according to claim 8 is characterized in that: The fill light (6) has an adjustable angle.

Images