Preparation of ZrB₂-SiC Powders via Carbothermal Reduction of Zircon and Prediction of Product Composition by Back-Propagation Artificial Neural Network

Abstract

Phase pure ZrB₂-SiC composite powders were prepared after 1 450 °C/3 h via carbothermal reduction route, by using ZrSiO₄, B₂O₃ and carbon as the raw materials. The influences of firing temperature as well as the type and amount of additive on the phase composition of final products were detailedly investigated. The results indicated that the onset formation temperature of ZrB₂-SiC was reduced to 1 400 °C by the present conditions, and oxide additive (including CoSO₄·7H₂O, Y₂O₃ and TiO₂) was effective in enhancing the decomposition of raw ZrSiO₄, therefore accelerating the synthesis of ZrB₂-SiC. Moreover, microstructural observation showed that the as-prepared ZrB₂ and SiC respectively had well-defined hexagonal columnar and fibrous morphology. Furthermore, the methodology of back-propagation artificial neural networks (BP-ANNs) was adopted to establish a model for predicting the reaction extent (e g, the content of ZrB₂-SiC in final product) in terms of various processing conditions. The results predicted by the as-established BP-ANNs model matched well with that of testing experiment (with a mean square error in 10^-3 degree), verifying good effectiveness of the proposed strategy.

Keywords

ZrB₂-SiC powders / carbothermal reduction / back-propagation artificial neural networks (BP-ANNs) / composition prediction

References

[1] Fahrenholtz W G, Hilmas G E, Talmy I G, et al. Refractory Diborides of Zirconium and Hafnium[J]. J. Am. Ceram. Soc., 2007, 90(5): 1347-1364.

[2] Yuan H P, Li J G, Shen Q, et al. Preparation and Microstructure of Porous ZrB₂ Ceramics using Reactive Spark Plasma Sintering Method[J]. J. Wuhan Univ. Technol.-Mater. Sci. Ed., 2015, 30(3): 512-515.

[3] Cao Y N, Zhang H J, Li F L, et al. Preparation and Characterization of Ultrafine ZrB₂-SiC Composite Powders by a Combined Sol-Gel and Microwave Boro/Carbothermal Reduction Method[J]. Ceram. Int., 2015, 41(6): 7823-7829.

[4] Deng X G, Du S, Zhang H J, et al. Preparation and Characterization of ZrB₂-SiC Composite Powders from Zircon via Microwave-Assisted Boro/Carbothermal Reduction[J]. Ceram. Int., 2015, 41(10): 14419-14426.

[5] Ryua H Y, Nersisyanb H H, Lee J H. Preparation of Zirconium-Based Ceramic and Composite Fine-Grained Powders[J]. Int. J. Refract. Met. Hard Mater., 2012, 30(1): 133-138.

[6] Zhang S W, Khangkhamano M, Zhang H J, et al. Novel Synthesis of ZrB₂ Powder via Molten-Salt-Mediated Magnesiothermic Reduction[J]. J. Am. Ceram. Soc., 2014, 97(6): 1686-1688.

[7] Tang P H, Song R G, Chai G Z, et al. Optimization of Laser Ablation Technology for PDPhSM Matrix Nanocomposite Thin Film by Artificial Neural Networks-Particle Swarm Algorithm[J]. J. Wuhan Univ. Technol.-Mater. Sci. Ed., 2010, 25(2): 188-193.

[8] Zhang H-J, Du S, Cao Y-N, et al. Investigation of Preparation of Ca-a-Sialon Powders via Artificial Neural Networks Analysis[J]. Ceram. Int., 2014, 40(1): 2287-2293.

[9] Zhang H J, Wang X J, Jia Q L, et al. Artificial Neural Network Analysis of Preparation of Nano a-Al₂O₃ Powders by Thermal Decomposition of Ammonium Aluminium Carbonate Hydroxide[J]. Mater. Sci. Technol., 2007, 23(9): 1021-1026.

[10] Basheer I A, Hajmeer M. Artificial Neural Networks: Fundamentals, Computing, Design and Application[J]. J. Microbiol. Meth., 2000, 43(1): 3-31.

[11] Guo D, Wang Y L, Xia J T, et al. Investigation of BaTiO₃ Formulation: An Artificial Neural Networks (ANNS) Method[J]. J. Eur. Ceram. Soc., 2002, 22(11): 1867-1872.

[12] Haykin S, Lippmann R. Neural Networks, a Comprehensive Foundation[J]. Int. J. Neural Syst., 1994, 5(4): 363-364.

[13] Hagan M T, Demuth H B, Beale M H, et al. Neural Network Design, 1996 Boston: PWS Publishing Company.