Activity Model Calculation in Slag Based on Artificial Intelligence and its Application in the Ternary Slag System

摘要: A model based on neural network for predicting the activity of components in multiple slag system is developed. The artificial nets can implement any approximation function with simple structure, while genetic algorith a globally optimized search one genetics and natural selection theory, which available to iteration process through alloying manipulation individuals colonies their restructuring then evolve increasingly improved approximate solutions generation by accordance adaptability individuals. GA always used give weight threshold nets. Computing simulating MnO-SiO2-Al2O3 FeO-MnO-SiO2 systems, it found that has high nonlinear capability computation results fit well relevant earlier works, thus enabling accurate prediction molten slag.