In recent years, artificial neural network (ANN) technology has developed rapidly and is now being applied across a broad range of fields. In the present paper, ANN models based on the BP algorithm are established in order to predict the volume contents of each component in multiphase ceramics. These models can predict the component contents of existing ceramics, and in addition they can successfully predict the component contents of unknown ceramic systems. The reliability of predictions relates closely to the precision of calculation. It is also shown by calculation that fault tolerance is good, so that the method will be useful in the development of multiphase ceramics.
Get full access to this article
View all access options for this article.
References
1.
GUOJ.: J. Solid State Chem., 1992, 69, 108.
2.
GUOJ.: Mater. Eng., 1992, 3, 149.
3.
ZHANGG., YUEX. and JINZ.: J. Chin. Ceram. Soc., 1995, 23, 365.
4.
SIMPSONP. K.: ‘Artificial neural systems: foundations, paradigms, applications and implementations’, 125; 1990, New York, NY, Pergamon.
5.
MARENA., HARSTONC. and PAPR.: ‘Handbook of neural computing applications’, 215; 1990, San Diego, CA, Academic Press.
6.
CARPENTERW. C. Artif. Intell. Eng. Des., 1997, 23, (11), 33.
7.
RUMELHARTD. and MCCLELLANDJ.: ‘Parallel distributed pro-cessing: explorations in the microstructure of cognition’; 1986, Cambridge, MA, MIT Press.
8.
XUL., HUANGY. and LIJ.: J. Chin. Ceram. Soc., 1998, 26, 14.
9.
DENGJ.: PhD thesis, Shandong University of Technology, China.
10.
XuC.: PhD thesis, Shandong University of Technology, China.
