Intelligent rutile single crystal growth control method based on computer vision feedback

A technology of computer vision and intelligent control, applied in computing, computing models, machine learning, etc., can solve problems such as large stress, high dislocation density, and unevenness

Active Publication Date: 2020-10-09
SHENYANG INST OF ENG
View PDF11 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the traditional crystal growth furnace is used. Since many growth process parameters cannot be accurately controlled, it is only possible to manually observe the crystal growth rate, growth shape, temperature distribution and composition distribution in the entire growth chamber, and then manually adjust the control parameters. The adjustment is mainly based on the experience of the operator, and no strict data relationship has been formed, resulting in a low success rate of crystal growth, and this will lead to structural integrity problems in the grown crystal, such as high dislocation density, large stress, and unstable Evenly etc.
During the crystal growth process, it is necessary to observe the crystal shape in real time and adjust the given speed of raw materials, so that each equipment operator operates at most two crystal growth furnaces, and operates the equipment while observing, and is often in a hurry, resulting in "flowing" in the early stage of crystal growth. "Phenomenon, which affects the success rate of crystal growth and increases the labor intensity of controlling crystal growth
[0004] At present, the rutile crystal market is monopolized by Japanese companies, and the success rate of crystal growth is not high, about 30%, and it cannot be mass-produced, which greatly limits the application of rutile crystals

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
  • Intelligent rutile single crystal growth control method based on computer vision feedback
  • Intelligent rutile single crystal growth control method based on computer vision feedback
  • Intelligent rutile single crystal growth control method based on computer vision feedback

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0050] see figure 1 combine figure 2 Shown: An intelligent control method for rutile single crystal growth based on computer vision feedback, including:

[0051] Step 1, utilize the high-definition video acquisition system to complete the collection of image information, and image preprocessing by the high-definition video acquisition system;

[0052] Step 2, the computer uses OPENCV to analyze the image features to realize image segmentation and feature point location;

[0053] Step 3, using the convolutional neural network to analyze the current real-time morphology of crystal growth on the processed image to the charact...

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 belongs to the field of new materials, and particularly relates to an intelligent rutile single crystal growth control method based on computer vision feedback, which comprises the following steps: acquiring image information by using a high-definition video acquisition system, and preprocessing an image by using the high-definition video acquisition system; using OPENCV to analyze image features by a computer to realize image segmentation and feature point positioning; performing crystal growth current real-time form analysis on crystal growth state characteristics of the processed image by using a convolutional neural network; comparing the analysis result with an edge coordinate curve of a healthy crystal growth form obtained by machine learning, and judging whether the crystal form is normal or not; and if yes, continuing to use the original given function curve to carry out growth control, and if not, adjusting the position of the combustion table and the feeding parameters through self-service adjustment, and implementing feedback images. Various parameters of crystal growth can be accurately controlled, and temperature distribution, composition distribution andmechanical distribution in the growth chamber are guaranteed.

Description

technical field [0001] The invention belongs to the field of new materials, in particular to an intelligent control method for rutile single crystal growth based on computer vision feedback. Background technique [0002] Because of its high birefringence and chemical stability, rutile single crystal has irreplaceable advantages in the preparation of optical isolators, optical circulators, polarizers and other devices. Single crystals of high temperature oxides, such as rutile, are traditionally grown using conventional flame fusion crystal growth furnaces. [0003] High-temperature oxide single crystals have special physical and chemical properties and play an important role in scientific research and modern social life. For example, rutile (TiO2) single crystal has large birefringence and high refractive index, and is used in spectral prisms and polarizing devices, such as optical isolators, optical circulators, and beam splitters. The above-mentioned devices currently us...

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 Applications(China)
IPC IPC(8): G06T7/10G06T7/13G06T7/73G06N3/04G06N20/00
CPCG06T7/10G06T7/13G06T7/73G06N20/00G06N3/045
Inventor 赵韦仑毕孝国赵琰王艳张东唐坚董颖男
Owner SHENYANG INST OF ENG
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