Applying ANN to analyze the influence on the recovery of chrome after silicon and aluminums' melting of 15-5PH(V) in EAF
Jee-Ray Wang, Pin-Yu Hsueh, Ping-You Zeng, Pin-Hung Chu · 2011
This study applies the artificial neural network to analyze the influence on the recovery of silicon and aluminum components of high and low levels after the melting in EAF, to look for the best recovery of chromium. First, to measure chrome content before EAF's melting. After the melting, the recovery is achieved by measuring the steel water, and the experimental data are trained by using Back propagation, and to obtain the best model. The accuracy of ANN in RMS is 1.51%, and the mean relative error is 1.43%, which can achieve the best chrome recovery.