An intelligent identification method and identification device for silicon material quality

A silicon material and intelligent technology, applied in the field of intelligent identification method and identification device of silicon material quality, can solve problems such as low work efficiency, difficulty in determining abnormal materials, and different judgment standards, so as to improve work efficiency, avoid classification errors, Identify the effect of classification accuracy

Active Publication Date: 2018-06-01
ASIA SILICON QINGHAI
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the prior art, the classification of silicon material products is made by the staff according to the classification standards. In actual work, there are many human factors affecting the judgment, and some abnormal materials are difficult to determine. Sometimes it is caused by sorting personnel or random inspection. Different judgment standards of personnel lead to inconsistent product classification, low work efficiency, and secondary pollution of silicon material products in the process of manual sorting

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An intelligent identification method and identification device for silicon material quality
  • An intelligent identification method and identification device for silicon material quality
  • An intelligent identification method and identification device for silicon material quality

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] see figure 1 , the present embodiment provides a method for intelligent identification of silicon material quality, comprising the following steps:

[0025] Step 100, the silicon material is placed on the conveying device, and is detected by the detecting device during the conveying process.

[0026] Step 110, extract the shape information to be recognized and the shape feature vector of the shape information sample according to the preset deep learning model, and calculate the similarity between the shape information to be recognized and the shape information sample based on the extracted shape feature vector value; according to the calculated similarity value, the shape information to be recognized is identified and classified.

[0027] For details below, see figure 2 .

[0028] Step 200, breaking the silicon rods into silicon materials, and breaking them to facilitate the analysis of the surface structure of the silicon materials.

[0029] Preferably, the steps ...

Embodiment 2

[0047] see image 3 , this embodiment provides an intelligent identification device 300 for the quality of silicon materials, including a crushing device 310 , a screening device 320 , a conveying device 330 , a detection device 340 , a control device 350 and a plurality of loading devices 360 .

[0048] The crushing device 310 is used to crush silicon rods to obtain silicon materials. Preferably, the crushing device 310 is located above the conveying device 330 , and the silicon material obtained after crushing the silicon rods by the crushing device 310 falls directly on the conveying device 330 , which facilitates the transportation of the conveying device 330 .

[0049] During the crushing process of the silicon rods by the crushing device 310 , powder and fine particles are generated, which are removed by the screening device 320 . Preferably, the screening device 320 is set on the conveying device 330, and the silicon material is screened during the conveying process. T...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides an intelligent identification method and an identification device for the quality of silicon materials, which belong to the technical field of silicon material production. The identification method includes placing the silicon material on the conveying device, detecting the surface morphology of the silicon material through the detection device during the conveying process, collecting the shape information, and calculating the number to be identified through the preset deep learning model based on the collected shape information. The similarity value between the shape information and the shape information sample is used to identify the shape information to be recognized, and the control device controls the conveying device to transport the silicon material to the corresponding loading device according to different classifications. The identification device includes a conveying device for conveying the silicon material, a detection device, a control device and a plurality of loading and unloading devices for containing the classified silicon material, and the detection device cooperates with the control device to classify the silicon material. The identification method of the identification device avoids the secondary pollution of the silicon material by manual identification and classification, and at the same time, the identification is more accurate.

Description

technical field [0001] The invention relates to the technical field of silicon material production, in particular to an intelligent identification method and identification device for the quality of silicon material. Background technique [0002] There are many types of silicon materials. For example, according to the technical requirements of polysilicon, the silicon materials produced are classified into rod-shaped silicon materials, massive silicon materials, and granular silicon materials, and silicon materials are classified according to the structure and surface density of silicon materials. The appearance of the material is divided into dense material, cauliflower material, coral material and dense block material, dense bar material, cauliflower block material, cauliflower bar material, coral block material, coral bar material, etc. Special silicon materials such as silicon core peeling, silicon core abnormality, fish scales, dendrites, burnt flow, interlayer, carbon ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G01N21/89G06K9/62G06N3/08
CPCG06N3/08G01N21/89G06F18/214
Inventor 宗冰王生红王体虎
Owner ASIA SILICON QINGHAI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products