Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for predicting solid-liquid interface of Czochralski method monocrystalline silicon based on ANN

A prediction method and technology of single crystal silicon, which is applied in the self-melting liquid pulling method, single crystal growth, single crystal growth and other directions, can solve the problems of time-consuming, complicated calculation, and the growth process parameters do not have an explicit relationship, and achieve The effect of shortening calculation time, improving crystal quality, and saving R&D expenses

Active Publication Date: 2020-07-03
包头美科硅能源有限公司 +1
View PDF10 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Currently in numerical simulation, the method of controlling the solid-liquid interface by adjusting the crystal rotation speed, crucible rotation speed, and pulling speed at specific intervals within a certain range cannot guarantee that the obtained process parameters are optimal. Non-linear strong coupling characteristics, complex calculation, time-consuming
In addition, the CZ single crystal silicon growth system involves many growth process parameters, and there is no explicit relationship between the growth process parameters and the crystal quality. It is difficult to quickly obtain the relationship between many growth parameters and crystal quality by relying on traditional numerical simulation methods relation

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
  • Method for predicting solid-liquid interface of Czochralski method monocrystalline silicon based on ANN
  • Method for predicting solid-liquid interface of Czochralski method monocrystalline silicon based on ANN
  • Method for predicting solid-liquid interface of Czochralski method monocrystalline silicon based on ANN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them.

[0028] according to figure 1 The flow chart includes the following steps:

[0029] Step 1: Establish a data set by numerical simulation of heat transfer of single crystal silicon by pulling method

[0030] Gambit software is used to generate the global calculation grid of pulling method single crystal silicon, which mainly includes areas such as quartz crucible, graphite baffle, crystal, melt, guide tube and protective gas. The finite volume method is used to solve the mass, momentum and energy equations in the growth furnace, the interface tracking method is used to simulate the phase transition process, and a global two-dimensional axisymmetric heat ...

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 discloses a method for predicting a solid-liquid interface of Czochralski method monocrystalline silicon based on ANN. The method comprises the following steps: firstly, establishing a two-dimensional global heat transfer numerical model of a Czochralski method monocrystalline silicon growth furnace by adopting a finite volume method; carrying out numerical simulation under each process parameter, collecting simulation data of monocrystalline silicon growth and arranging the simulation data into a data set; dividing the data set into a training set and a test set, performing normalization processing, determining a machine learning algorithm, establishing a prediction model of the quality of the Czochralski method monocrystalline silicon, and evaluating the reliability of themodel. And then, calculating the growth quality of the monocrystalline silicon by utilizing the prediction model, and evaluating a prediction result on the test set. And finally, predicting an optimalgrowth condition. According to the method, the key factors influencing the quality of the Czochralski method monocrystalline silicon can be quickly found out, and the crystal quality under the key factors is accurately predicted, so that proper growth conditions are obtained, the research and development efficiency is improved, the expenditure is saved, and the large-size and high-quality monocrystalline silicon is grown.

Description

technical field [0001] The invention relates to a method for detecting the quality of silicon single crystal products, in particular to an ANN-based method for predicting the solid-liquid interface of single crystal silicon in a pulling method. Background technique [0002] Silicon single crystal is an indispensable basic material for industries such as integrated circuits and solar photovoltaic power generation. With the rise of emerging technologies such as 5G and artificial intelligence and the popularization of solar photovoltaic power generation, its demand is increasing day by day. Large diameter, high quality, and low cost are the future development trends of silicon single crystal. [0003] Czochralski (CZ) single crystal silicon growth technology is the mainstream method for preparing silicon single crystal. However, as the crystal size increases, the latent heat of crystallization released at the solid-liquid interface increases sharply, making it more difficult t...

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
IPC IPC(8): G06F30/20G06N3/04G06N3/08G06N20/00C30B15/20C30B29/06G06F111/10G06F119/08
CPCG06N3/08G06N20/00C30B15/20C30B29/06G06N3/045Y02P90/30
Inventor 齐小方王艺澄姚亮黄振华
Owner 包头美科硅能源有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products