Boron removal from metallurgical grade silicon by slag refining based on GA-BP neural network

  • SCI-E
  • EI
作者: Yuan, Shi-Lai;Lu, Hui-Min;Wang, Pan-Pan;Tian, Chen-Guang;Gao, Zhi-Jiang
通讯作者: Lu, H.-M.(13331151800@126.com)
作者机构: School of Materials Science and Engineering, Beijing University of Aeronautics and Astronautics, Beijing, 100191, China
语种: 英文
关键词: Back propagation neural networks - Boron in silicon - BP neural networks - Ga-bp neural networks - Intermediate frequencies - Metallurgical grade silicons (MGSi) - Oxygen potential - Slag compositions
期刊: RARE METALS
年: 2021
卷: 40
期: 1
页码: 237-242
基金类别: financially supported by the National High Technology Research and Development Program of China (No.2012AA062302);
摘要: In order to investigate the boron removal effect in slag refining process, intermediate frequency furnace was used to purify boron in SiO<inf>2</inf>-CaO-Na<inf>3</inf>AlF<inf>6</inf>-CaSiO<inf>3</inf> slag system at 1,550 &deg;C, and back propagation (BP) neural network was used to model the relationship between slag compositions and boron content in SiO<inf>2</inf>-CaO-Na<inf>3</inf>AlF<inf>6</inf>-CaSiO<inf>3</inf> slag system. The BP neural network predicted error is below 2.38 %. The prediction results show that the slag composition has a significant influence on boron removal. Increasing the basicity of slag by adding CaO or Na<inf>3</inf>AlF<inf>6</inf> to CaSiO<inf>3</inf>-based slag could contribute to the boron removal, and the addition of Na<inf>3</inf>AlF<inf>6</inf> has a better removal effect in comparison with the addition of CaO. The oxidizing characteristic of CaSiO<inf>3</inf> results in the ineffective removal with the addition of SiO<inf>2</inf>. The increase of oxygen potential ((Formula presented.)) in the CaO-Na<inf>3</inf>AlF<inf>6</inf>-CaSiO<inf>3</inf> slag system by varying the SiO<inf>2</inf> proportion can also contribute to the boron removal in silicon ingot. The best slag composition to remove boron was predicted by BP neural network using genetic algorithm (GA). The predicted results show that the mass fraction of boron in silicon reduces from 14.0000 &times;10<sup>-6</sup> to 0.4366 &times;10<sup>-6</sup> after slag melting using 23.12 % SiO<inf>2</inf>-10.44 % CaO-16.83 % Na<inf>3</inf>AlF<inf>6</inf>-49.61 % CaSiO<inf>3</inf> slag system, close to the experimental boron content in silicon which is below 0.5 &times;10<sup>-6</sup>. &copy;2014 The Nonferrous Metals Society of China and Springer-Verlag Berlin Heidelberg.

文件格式:
导出字段:
导出
关闭
Boron removal from metallurgical grade silicon by slag refining based on GA-BP neural network
有问题请联系我们,邮箱:常见的失败原因