Our website is currently undergoing maintenance. Article records and full texts remain available. Submissions can be made through the Editorial Manager.

Modelling the Wear of MC 98/15 Refractory Material in the Slag Spout Zone of an Oxygen Converter with the Use of Artificial Neural Networks

W. Zelik, R. Lech, S. Sado, A. Labuz, A. Lasota, S. Lis

Journal of Ceramic Science and Technology, Vol. 11, No. 2 (2020), pp. 81-90

DOI: 10.4416/JCST2020-00009

Download full article (PDF)

Abstract

In oxygen converters, the high temperature and aggressive alloys affect the refractory lining, which is most frequently made of MgO-C materials. The refractory lining of a converter is worn zonally along with the progress of the campaign. This paper describes a trial conducted to forecast the wear of the refractory material depending on the selected parameters of the metallurgical process. Based on the results of industrial measurements, a wear model of the magnesia-carbon refractory material for the converter slag spout zone was developed. For the construction of the model, multilayer artificial neural networks were used. The accuracy of the forecast of the refractory material wear in the wear classes achieved in the experiment equals 63.9 % with the network architecture consisting of the following numbers of the neurons 17: h(20,10,5) :10, where the parameter h(20,10,5) contains the number of neurons in individual hidden layers. The calculations were made i.a. in the R language and environment.

Keywords

Refractories, MgO-C, BOF converter, artificial neural network, statistical analysis

View this issue · Article & DOI index