Activity Model Calculation in Slag Based on Artificial Intelligence and its Application in the Ternary Slag System
A model based on neural network for predicting the activity of components in multiple slag system is developed. The artificial neural nets can implement any approximation of function with simple structure, while the genetic algorith is a globally optimized search one based on genetics and natural selection theory, which is available to implement the iteration process through alloying the genetic manipulation to the individuals in colonies for their restructuring and then evolve the increasingly improved approximate solutions generation by generation in accordance to the adaptability function for individuals. GA is always used to give the weight and threshold of neural nets. Computing and simulating the MnO-SiO2-Al2O3 and FeO-MnO-SiO2 slag systems, it is found that the model has high nonlinear capability and the computation results fit well with that in relevant earlier works, thus enabling the accurate prediction of the activity of components in molten slag.
Guangfan Li, Yong Huang and Chaohe Chen
Z. H. Jiang et al., "Activity Model Calculation in Slag Based on Artificial Intelligence and its Application in the Ternary Slag System", Advanced Materials Research, Vols. 250-253, pp. 4052-4056, 2011