The artificial neural network approach for optimization of lining resi
stance of basic oxygen furnace is presented in this paper. A group of
samples has been collected to study. 33 samples are divided into two c
lasses, i.e. good samples (class 1) providing a furnace life of more t
han 1000 heats, and bad samples (class 2) meaning a furnace life of le
ss than 1000 heats. Analysis of 18 factors influencing furnace life sh
ows that the major factors are supplementary filling amount, blowing t
ime, melting time, and production rate. In this research, 25 samples a
re used as learning material, while eight samples are used as testing
material for the natural network. The factors of major influence are t
aken as input variables. As a result, the testing rate reaches 100%, w
hich indicates that the model trained is reliable. In order to increas
e the furnace life according to the model, the partial derivative valu
e of the output to each feature variable at the average point of class
-2 samples was calculated. The results show, that, whereas blowing and
melting time had to be decreased, both the supplementary filling amou
nt and production rate had to be increased. This result is quite consi
stent with the practical experience obtained in the plant. In addition
, the neural network approach also has a fault-tolerant ability, predi
ction and optimization speed. To sum up, the neural network approach m
ight be referred to as an effective assistant technique for optimizati
on of iron and steel industry.