MOLTEN SALT PHASE DIAGRAMS CALCULATION USING ARTIFICIAL NEURAL NETWORK OR PATTERN RECOGNITION-BOND PARAMETERS
Part2. Prediction of phase diagrams of ternary molten salt systems
Part2. Prediction of phase diagrams of ternary molten salt systems
(1.Department of Mineral Engineering, Central South University of Technology,Changsha 410083, P. R. China;
2.Shanghai Institute of Metallurgy, Chinese Academy of Sciences, Shanghai200050, P. R. China)
2.Shanghai Institute of Metallurgy, Chinese Academy of Sciences, Shanghai200050, P. R. China)
Abstract: Using pattern recognition method or the three layered-artificial neural network (ANN) method with back propagation algorithm, and with chemical bond parameters as features or inputs, the properties or characteristics of the phase diagrams of some ternary molten salt systems have been investigated. The trained ANN was used to predict the formability of ternary intermediate compound, the type of phase diagram. Moreover, the results of computerized prediction for two unknown systems are confirmed by experimental work.
Key words: phase diagram calculation artificial neural netwrok pattern recognition bond parameter ternary molten salt system