The use of neural-network-based technologies to analyze the effects of a combination blast on blast-furnace performance indices was discussed. The modeling determines the control actions and develop recommendation which involves classical mathematical model of blast furnace smelting. The instructional neural networks were used to calculate the process parameters and develop network program which includes a file of excel tables and files with designs of neural networks. The new approach solves two main problems encountered in controlling smelting: lowering the coke rate and making more efficient and more productive use of natural gas or other fuel additions to the blast.