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

Method for preparing high-purity indium through multi-channel array type directional solidification based on machine learning

A directional solidification and machine learning technology, applied in machine learning, instruments, manufacturing tools, etc., can solve problems such as the interaction of parameter complexity and difference in results, and achieve uniform heating temperature gradient distribution, stable temperature field, and strong controllability Effect

Pending Publication Date: 2022-07-29
云南锡业集团(控股)有限责任公司研发中心
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the complexity of parameters and the interaction between parameters, the results obtained by different researchers are also different

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 preparing high-purity indium through multi-channel array type directional solidification based on machine learning
  • Method for preparing high-purity indium through multi-channel array type directional solidification based on machine learning
  • Method for preparing high-purity indium through multi-channel array type directional solidification based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] A method for preparing high-purity indium by multi-channel array directional solidification based on machine learning, the method steps are as follows:

[0025] S1. Purify indium under different directional solidification speed conditions first, the process is as follows:

[0026] S1.1 obtains 5N indium by the electrolysis method of the prior art, evenly packs it into 9 quartz boats, puts it into the quartz tube 12 of the three-by-three-array type multi-channel directional solidification furnace 6, closes the quartz tube, and starts the electrical control device. Open the control cabinet button 8 of the electrical control device, set the process parameters such as zone melting speed, zone melting times, gas flow, etc. on the panel 9, and open the vacuum system and protective gas system 5 of the three-by-three-array multi-channel directional solidification furnace. The air release valve 11 is evacuated, and the protective gas nitrogen is introduced, and the gas flow is ...

Embodiment 2

[0033] A method for preparing high-purity indium by multi-channel array directional solidification based on machine learning, and the purification of indium under the conditions of different directional solidification times is as follows:

[0034] (1) Put the 5N indium obtained by electrolysis into 9 quartz boats, put it into the quartz tube in the three-by-three-array multi-channel directional solidification furnace, close the quartz tube, start the electrical control device, evacuate, and pass the Protective gas hydrogen, the gas flow rate is 0.5L / min;

[0035] (2) The widths of the three-by-three-array-type multi-channel heaters of the three-by-three-array-type multi-channel directional solidification furnace are set to 20mm and 30mm, respectively, and they move directionally at the speed of 20mm / h and 30mm / h respectively, and the directional solidification is 1 ~6 times, the melting zone temperature is 180-200℃;

[0036] (3) Stop the furnace after the operation is complet...

Embodiment 3

[0038] Based on the high-purity indium prepared in the above embodiment 2, machine learning is used to optimize the preparation of high-purity indium, and machine learning prediction of the high-purity indium database is performed, and the method is as follows:

[0039] S2. Construct a high-purity indium directional solidification data set: collect and record the moving speed of the directional solidification furnace, heater width, solidification times, melting zone temperature and the purity of product indium under the corresponding parameters obtained in the above step S1, and construct a table. The high-purity indium directional solidification dataset shown in 1 is used for subsequent data mining;

[0040] S3. Build a high-purity indium directional solidification process machine learning model: based on the process parameters of the above-mentioned embodiments, including heater moving speed, heater width, solidification times, melting zone temperature, gas flow rate, etc., a...

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 relates to a method for preparing high-purity indium by multi-channel array directional solidification based on machine learning, which is characterized in that 5N indium prepared by an electrolysis method is used as a raw material, and the raw material is put into a vacuum chamber for array multi-channel directional solidification purification to obtain uniformly arranged 6N and above high-purity indium products. According to the method, a machine learning method is combined, various machine learning prediction models are established, the accuracy of the models is evaluated through ten-fold cross validation, different machine learning models are compared and evaluated, the optimal machine learning model is screened out, and the optimal experimental parameter range of directional solidification of high-purity indium is predicted; and the method has the advantages of high selectivity, high purification efficiency and strong controllability, and can provide high-quality high-purity metal materials for the semiconductor industry.

Description

technical field [0001] The invention belongs to the technical field of high-purity material purification and directional solidification, in particular to a method for preparing high-purity indium based on machine learning-assisted multi-channel array directional solidification. Background technique [0002] High-purity indium plays a key role in the indium industry chain. Due to its excellent light permeability and strong electrical conductivity, high-purity indium is mainly used to make semiconductor compounds, high-purity alloys and dopants of semiconductor materials. In the field of optoelectronics, indium and its compound semiconductors have a wide range of uses, mainly synthesizing indium-based III-V compound semiconductors such as indium antimonide (InSb), indium phosphide (InP), indium arsenide (InAs), etc., as optical fiber communication The requirements for the purity of indium metal are getting higher and higher for laser light sources, heterojunction solar cell ma...

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): C22B58/00C22B9/16B22D27/04B22D46/00G06K9/62G06N20/00G06Q10/04
CPCC22B58/00C22B9/006C22B9/16B22D27/045B22D46/00G06Q10/04G06N20/00G06F18/217
Inventor 陈丽诗连正亨伍美珍彭巨擘贾元伟白海龙张家涛陆文聪
Owner 云南锡业集团(控股)有限责任公司研发中心
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com