Search

CN-224216593-U - Automatic recognition device for surface defects of panel glass

CN224216593UCN 224216593 UCN224216593 UCN 224216593UCN-224216593-U

Abstract

The utility model discloses an automatic recognition device for surface defects of panel glass, which comprises a detection platform, a light source system, an image acquisition module, an image processing unit and an adjustable mechanical support, wherein the detection platform is provided with a three-dimensional adjusting seat, the light source system comprises a multispectral light source assembly and a light path adjusting mechanism, and the multispectral light source assembly integrates a visible light source, an infrared light source and an ultraviolet light source through an optical fiber array. Through integration of multispectral light sources, dynamic light path adjustment, precise mechanical positioning and edge computing technology, an excitation-acquisition-processing full-link closed-loop system is constructed, and the bottlenecks of the traditional detection device in aspects of multi-defect type adaptability, dynamic detection precision, environment anti-interference capability and the like are solved.

Inventors

  • LIU LEI
  • FENG JINGFEI

Assignees

  • 东莞市摩尔智能科技有限公司

Dates

Publication Date
20260508
Application Date
20250526

Claims (7)

  1. 1. The automatic recognition device for the surface defects of the panel glass comprises a detection platform, a light source system, an image acquisition module, an image processing unit and an adjustable mechanical support, and is characterized in that the detection platform is provided with a three-dimensional adjustment seat, the light source system comprises a multispectral light source component and a light path adjustment mechanism, the multispectral light source component integrates a visible light source, an infrared light source and an ultraviolet light source through an optical fiber array, the light path adjustment mechanism comprises a rotating base arranged at the edge of the detection platform, a liftable reflecting prism group is arranged on the rotating base, and the reflecting prism group is arranged opposite to a light emitting end of the multispectral light source component; The image acquisition module is arranged at the front end of the cantilever beam of the adjustable mechanical support through the three-dimensional adjusting seat, the cantilever beam is in sliding connection with the linear guide rail, the linear guide rail is controlled by the servo driving assembly, and the image processing unit is internally provided with an edge computing chip and is in communication connection with the image acquisition module through the gigabit Ethernet interface.
  2. 2. The automatic recognition device for the surface defects of the panel glass according to claim 1, wherein the three-dimensional adjusting seat comprises an X-direction sliding rail, a Y-direction sliding rail and a Z-direction screw rod which are arranged vertically, the image acquisition module carries out vertical height adjustment through the Z-direction screw rod, and carries out horizontal position fine adjustment through the X-direction sliding rail and the Y-direction sliding rail.
  3. 3. The automatic recognition device for the surface defects of the panel glass according to claim 1, wherein the servo driving assembly comprises a rack arranged in parallel with the linear guide rail and a gear meshed with the rack, and the gear is in transmission connection with the servo motor.
  4. 4. The automatic recognition device for the surface defects of the panel glass according to claim 1, wherein a vacuum adsorption platform is arranged on the surface of the detection platform, an infrared correlation sensor is arranged around the edge of the vacuum adsorption platform, and the infrared correlation sensor is electrically connected with the servo driving assembly.
  5. 5. The automatic recognition device for the surface defects of the panel glass according to claim 1, wherein an air-floating shock-absorbing base is arranged at the bottom of the adjustable mechanical support, and comprises a rubber vibration isolation layer and an air pressure balance valve.
  6. 6. The apparatus of claim 1, wherein the multispectral light source assembly is configured with a wavelength switch controller, and the wavelength switch controller is connected to the visible light source, the infrared light source or the ultraviolet light source through a relay set.
  7. 7. The automatic identification device for the defects of the surface of the panel glass according to claim 1, wherein the vibration isolation supporting assembly is arranged at the bottom of the detection platform and comprises a supporting seat fixedly connected with the detection platform, a rubber vibration isolation pad arranged below the supporting seat and a leveling bolt penetrating through the supporting seat and the rubber vibration isolation pad.

Description

Automatic recognition device for surface defects of panel glass Technical Field The utility model relates to the technical field of detection equipment, in particular to an automatic recognition device for surface defects of panel glass. Background In the fields of consumer electronics, flat panel display, architectural glass and the like, surface defects (such as cracks, bubbles, scratches and the like) of panel glass directly affect the quality and reliability of products, so that high-precision surface defect detection is a key link of a production flow. The traditional detection method relies on manual visual or single light source imaging, and has the problems of low detection efficiency, high omission factor, high labor cost and the like. The existing automatic detection equipment introduces a machine vision technology, but has the defects that firstly, a light source system adopts a single spectrum, the detection requirements of surface flaws and internal flaws are difficult to meet, for example, sensitivity of ultraviolet bands to microcracks and penetrability advantages of infrared bands to interlayer impurities are not fully utilized, secondly, an optical path adjusting mechanism is fixed, an incident angle cannot be dynamically adjusted according to the surface roughness of glass, so that detection compatibility of glass made of different materials is poor, thirdly, the positioning accuracy of an image acquisition module is insufficient, effective vibration isolation measures are lacked, image blurring is easy to occur in a high-speed production line environment, fourthly, workpiece positioning depends on manual placement, the degree of automation is low, and the full-width detection requirements of large-size glass are difficult to adapt. Disclosure of utility model In order to overcome the defects of the prior art, the utility model provides an automatic recognition device for the surface defects of panel glass, which can effectively solve the problems of the background art. The technical scheme adopted for solving the technical problems is as follows: the utility model provides a panel glass surface defect automatic identification device, includes testing platform, light source system, image acquisition module, image processing unit and adjustable mechanical support, testing platform is equipped with three-dimensional regulation seat, light source system includes multispectral light source subassembly and light path adjustment mechanism, multispectral light source subassembly passes through fiber array integrated visible light source, infrared light source and ultraviolet light source, light path adjustment mechanism is including installing in the rotating base at testing platform edge, set up liftable reflection prism group on the rotating base, reflection prism group with multispectral light source subassembly's light-emitting end sets up relatively; The image acquisition module is arranged at the front end of the cantilever beam of the adjustable mechanical support through the three-dimensional adjusting seat, the cantilever beam is in sliding connection with the linear guide rail, the linear guide rail is controlled by the servo driving assembly, and the image processing unit is internally provided with an edge computing chip and is in communication connection with the image acquisition module through the gigabit Ethernet interface. As further description of the technical scheme, the three-dimensional adjusting seat comprises an X-direction sliding rail, a Y-direction sliding rail and a Z-direction screw rod which are arranged vertically to each other, the image acquisition module carries out vertical height adjustment through the Z-direction screw rod, and carries out horizontal position fine adjustment through the X-direction sliding rail and the Y-direction sliding rail. As a further description of the above technical solution, the servo driving assembly includes a rack parallel to the linear guide rail and a gear engaged with the rack, and the gear is in transmission connection with the servo motor. As further description of the technical scheme, the vacuum adsorption platform is arranged on the surface of the detection platform, the infrared correlation sensor is arranged around the edge of the vacuum adsorption platform, and the infrared correlation sensor is electrically connected with the servo driving assembly. As further description of the technical scheme, the bottom of the adjustable mechanical support is provided with an air-floating shock-absorbing base, and the air-floating shock-absorbing base comprises a rubber vibration isolation layer and an air pressure balance valve. As a further description of the above technical solution, the multispectral light source assembly is configured with a wavelength switching controller, and the wavelength switching controller is connected with the visible light source, the infrared light source or the ultraviolet light source through a rel