CN214794502U

CN214794502U - Intelligent detection system for surface defects of bare chip

Info

Publication number: CN214794502U
Application number: CN202120121632.9U
Authority: CN
Inventors: 杜林�; 圣冬冬; 王海涛; 楼建设; 游君; 刘港港
Original assignee: SHANGHAI PRECISION METROLOGY AND TEST RESEARCH INSTITUTE
Current assignee: SHANGHAI PRECISION METROLOGY AND TEST RESEARCH INSTITUTE
Priority date: 2021-01-16
Filing date: 2021-01-16
Publication date: 2021-11-19
Anticipated expiration: 2031-01-16

Abstract

The utility model provides an intelligent detection system for surface defects of bare chips, which comprises a camera, a lens, a lifting bracket, a detection workbench and a computer; the bare chip is placed on a detection workbench, and the detection workbench moves back and forth and left and right through a guide rail; the lens is arranged at the front end of the camera and used for amplifying the acquired bare chip image, and the lens is positioned right above the detection workbench; the camera is arranged on the lifting bracket, and moves up and down through the lifting bracket to adjust the distance between the camera and the bare chip; the computer is connected with the camera through a network cable, the bare chip image collected by the camera is processed, the bare chip image is identified through the detection model, whether the bare chip has defects or not is judged, and when the bare chip has defects, the computer alarms through the connected alarm. The utility model discloses effectively avoided missing the emergence of examining the condition, promoted defect identification detection efficiency by a wide margin, reduced artifical intensity of labour.

Description

Intelligent detection system for surface defects of bare chip

Technical Field

The utility model belongs to the technical field of the chip detects, in particular to bare chip surface defect intelligent detection system.

Background

In the field of surface quality inspection of semiconductor chips, more and more high-end equipment manufacturers are beginning to apply machine vision technology to perform automatic inspection of chip surface defects, such as Cognex, VMT, japan KEYENCE, singapore STI, etc., and can provide a complete solution for chip surface defect inspection. The research of our country in the field of machine vision starts late, and the research and application in the semiconductor chip industry at present mainly focuses on occasions such as character recognition, chip surface printing quality detection and the like, and the occasions such as chip surface quality detection and defect classification still depend on foreign products. With the development of artificial intelligence technology, the defect detection method based on machine learning is widely applied.

Many instruments for detecting the IC chip are available in foreign markets, but the instruments have single functions, can only detect some defects, have limitations on measurement range and working time, are complicated in operation process and expensive in price, and few Automatic Optical Inspection (AOI) devices are available in China for identifying defects such as scratches, foreign matters and edges in the appearance of the IC chip. Some manufacturers develop production line application of AOI foreign equipment, the use of visual inspection equipment greatly reduces manual pressure, but the accuracy rate cannot meet the high-quality requirement.

Although many studies at present realize preliminary chip automatic defect detection, most of the studies are used by a traditional computational vision method, and mainly aiming at packaged chips, the realized functions can only be suitable for single-type chip defect detection tasks and are difficult to realize defect positioning, and the classification tasks of aerospace microwave chips with various types lack a learning and summarizing process and are difficult to meet the requirements. Particularly for microwave bare chips, at present, related researches are few, a user unit with high reliability requirement performs quality control on the microwave bare chips, related data are firstly monitored and reviewed, different from packaged devices, the bare chips cannot be aged and screened, an artificial intelligent detection system capable of automatically identifying defects is urgently needed to be established, and the method has important significance for breaking high-end equipment and technical monopoly of foreign semiconductor package testing and improving the independent research and development capability of China in semiconductor chip package testing equipment.

SUMMERY OF THE UTILITY MODEL

In view of the above prior art's shortcoming, the utility model aims to provide a bare chip surface defect intelligent detection system, it is big to solve artifical mechanical repetition intensity of labour among the prior art, and detection efficiency is low, and the yield is not high to and the judgement standard that current AOI check out test set appears is non-uniform, easily leaks to examine, technical problem such as false retrieval.

The technical scheme adopted by the invention is as follows:

an intelligent detection system for surface defects of a bare chip comprises a camera, a lens, a lifting bracket, a detection workbench and a computer;

the bare chip is placed on a detection workbench, and the detection workbench moves back and forth and left and right through a guide rail;

the lens is arranged at the front end of the camera and used for amplifying the acquired bare chip image, and the lens is positioned right above the detection workbench;

the camera is arranged on the lifting bracket, and moves up and down through the lifting bracket to adjust the distance between the camera and the bare chip;

the computer is connected with the camera through a network cable, the bare chip image collected by the camera is processed, the bare chip image is identified through the detection model, whether the bare chip has defects or not is judged, and when the bare chip has defects, the computer alarms through the connected alarm.

Further, bare chip surface defect intelligent detection system still includes the light source, the light source is located the detection achievement platform top, installs on lifting support for the transmission beam, light source and camera synchronous motion.

Furthermore, the light source is installed on the lifting support through the connecting rod, a universal sleeve and a universal ball head are arranged between the light source and the connecting rod, the universal ball head is arranged in the universal sleeve, and the angle of the light source irradiating the bare chip is adjusted through the universal ball head.

Further, the camera adopts a CCD camera or a CMOS camera.

Further, the resolution of the camera is at least 2200 by 500 pixels.

Further, the lens adopts a zoom lens, and focal length conversion can be carried out within the range of 30mm-46 mm.

Further, the light source comprises a forward light source and a lateral light source, the optical axis of the forward light source is consistent with the optical axis of the camera, and the optical axis of the lateral light source is perpendicular to the optical axis of the camera.

Further, the light source is any one of a fluorescent lamp, an incandescent lamp, a tungsten halogen lamp, a metal halide lamp, an LED lamp, and a laser lamp.

Further, a rotating mechanism is installed at the bottom of the detection workbench, and the optimal photographing position between the camera and the bare chip is ensured through the rotating mechanism.

Further, the bare chip surface defect intelligent detection system also comprises a manipulator device used for grabbing the bare chip.

Compared with the prior art, the beneficial effects of the utility model are as follows: the condition of missing detection is effectively avoided, the defect identification and detection efficiency is greatly improved, and the labor intensity of workers is reduced.

Drawings

Fig. 1 is the utility model discloses bare chip surface defect intellectual detection system overall structure schematic diagram.

Detailed Description

The utility model provides a bare chip surface defect intellectual detection system, as shown in FIG. 1, including camera 2, camera lens 3, lifting support 6, testing workbench 1, computer 5 and light source 4. The bare chip 7 is placed on the detection workbench 1, and the detection workbench moves forward and backward and leftward and rightward through the guide rail. The lens 3 is arranged at the front end of the camera 2 and used for amplifying the collected bare chip image, and the lens 3 is positioned right above the detection workbench 1. The camera 2 is mounted on the elevating bracket 6, and moves up and down through the elevating bracket 6 to adjust the distance between the camera 2 and the bare chip 7. The lifting bracket 6 is arranged on the supporting frame 9. The computer 5 is connected with the camera 2 through a network cable, the bare chip image collected by the camera 2 is processed, the bare chip image is identified through the detection model, whether the bare chip 7 has defects or not is judged, and when the bare chip 7 has defects, the computer 5 gives an alarm through the connected alarm 8. The light source 4 is positioned above the detection workbench 1, is arranged on the lifting support 6 and is used for emitting light beams, and the light source 4 and the camera 2 move synchronously.

The resolution of the camera in the present embodiment requires at least 2200 × 500 pixels. According to the comprehensive consideration of factors such as detection precision, cost performance of a camera, results of different camera tests and the like, the German Basler Ace ACA2500-14gm industrial camera is preferably adopted, the resolution of the camera is adjusted to 2256 x 1500 pixels, and therefore the subsequent processing speed of images can be greatly improved while the problem detection precision is met.

In a defect detection system, the suitability of lens selection directly affects the overall performance of the system. In general, parameters such as an imaging plane, a working distance, a field of view, and a depth of field need to be considered when selecting a lens. The lens is an optical focalizer located in front of the camera, and the lens mainly has the function of enabling the camera to flexibly change the view angle, brightness and the like of a picture by adjusting the focal length and the aperture of the lens, and is an important element for image acquisition. The model of the lens must be determined according to the detected working distance.

In a specific embodiment, the distance between the camera and the bare chip is approximately 60mm, and a lens of Japanese computer PM-1614M is preferably used together with the camera, and the lens is a zoom lens which can realize the focal length conversion within the range of 30mm-46 mm. The camera and the lens are reasonably matched to acquire images of the bare chip.

Artificial light sources are generally used for defect detection, and mainly include fluorescent lamps, incandescent lamps, tungsten halogen lamps, metal halide lamps, Light Emitting Diodes (LEDs), laser lamps and the like. The influence of external environment light on the detection process can be greatly eliminated by adopting an artificial light source. The light source effect directly determines the imaging quality of the workpiece.

Considering that the bare chip contains a plastic part and a metal part, blindly selecting the light source can produce shadows and reflections. The existence of shadows can bring great difficulty to the analysis and identification of the whole image, and the reflection of light can make the defects on the surface of the chip unrecognizable. Therefore, in the light source selection, the shadow generated by the chip plastic and the light reflection phenomenon of the metal part must be eliminated. Thus, with reference to the nature of the die itself, a particular embodiment preferably employs a combination of light sources from Dongguan CST, including white coaxial light sources and bar LED light sources of model BL-66-11-R/G/B/W. The light source is placed in a certain requirement, in a specific embodiment, a mode of combining forward illumination and lateral illumination is adopted, the optical axis of the coaxial illumination light source is consistent with that of the camera, and the optical axis of the LED light source is perpendicular to that of the camera, so that the LED light source is a symmetrical illumination mode, and shadow and reflection can be better avoided.

Preferably, the supporting frame 9 is further provided with a manipulator, the manipulator can automatically carry the bare chip, the manipulator is driven by a linear motor, the manipulator is provided with a plurality of vacuum suction nozzles, the vacuum suction nozzles are communicated with an external vacuum generator, the bare chip is sucked by the vacuum suction nozzles, and the bare chip picking and placing device has the characteristics of high-precision positioning, picking and placing and high-speed movement.

It should be noted that the foregoing is only illustrative and illustrative of the present invention, and that any modifications and alterations to the present invention are within the scope of the present invention as those skilled in the art will recognize.

Claims

1. An intelligent detection system for surface defects of a bare chip is characterized by comprising a camera, a lens, a lifting bracket, a detection workbench and a computer;

the computer is connected with the camera through a network cable, the bare chip image collected by the camera is processed, the bare chip image is identified through the detection model, whether the bare chip has defects or not is judged, and when the bare chip has defects, the computer alarms through the connected alarm;

the intelligent detection system for the surface defects of the bare chip also comprises a light source, wherein the light source is positioned above the detection workbench, is arranged on the lifting support and is used for emitting light beams, and the light source and the camera move synchronously;

a universal sleeve and a universal ball head are arranged between the light source and the connecting rod, the universal ball head is arranged in the universal sleeve, and the angle of the light source irradiating the bare chip is adjusted through the universal ball head;

the bottom of the detection workbench is provided with a rotating mechanism, and the optimal photographing position between the camera and the bare chip is ensured through the rotating mechanism;

the intelligent detection system for the surface defects of the bare chip further comprises a manipulator device used for grabbing the bare chip.

2. The system of claim 1, wherein the camera is a CCD camera or a CMOS camera.

3. The system of claim 2, wherein the camera has a resolution of at least 2200 x 500 pixels.

4. The system of claim 1, wherein the lens is a zoom lens capable of performing a focus change within a range of 30mm-46 mm.

5. The system of claim 1, wherein the light source comprises a forward light source and a lateral light source, an optical axis of the forward light source is aligned with an optical axis of the camera, and an optical axis of the lateral light source is perpendicular to the optical axis of the camera.

6. The system of claim 1, wherein the light source is any one of a fluorescent lamp, an incandescent lamp, a tungsten halogen lamp, a metal halide lamp, an LED lamp, and a laser lamp.