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

Abstract

In order to investigate the boron removal effect in slag refining process, intermediate frequency furnace was used to purify boron in SiO2-CaO-Na3AlF6-CaSiO3 slag system at 1,550 °C, and back propagation (BP) neural network was used to model the relationship between slag compositions and boron content in SiO2-CaO-Na3AlF6-CaSiO3 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 Na3AlF6 to CaSiO3-based slag could contribute to the boron removal, and the addition of Na3AlF6 has a better removal effect in comparison with the addition of CaO. The oxidizing characteristic of CaSiO3 results in the ineffective removal with the addition of SiO2. The increase of oxygen potential ( $$p_{{{\text{O}}_{2} }}$$ ) in the CaO-Na3AlF6-CaSiO3 slag system by varying the SiO2 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 × 10−6 to 0.4366 × 10−6 after slag melting using 23.12 % SiO2-10.44 % CaO-16.83 % Na3AlF6-49.61 % CaSiO3 slag system, close to the experimental boron content in silicon which is below 0.5 × 10−6.