Kovacic, Miha;Jurjovec, Beno;Krajnc, Luka, Ladle nozzle opening and genetic programming

Abstract:

?tore Steel Ltd. faces a huge problem with ladle nozzle opening during the production of a wide variety of steel grades. After the ladle treatment the steel melt is poured from the ladle through the sliding gate and the nozzle into the tundish on the continuous casting machine. Due to often cloggings the ladle nozzle must be opened with the oxygen which can cause melt pollution. The purpose of this paper is to present the attempt for reducing ladle nozzle openings. In this attempt genetic programming method was used. The experimental data on 115 consequently casted heats was used. The steelmaking technology, number of heats in the sequence, ladle treatment time, inner and outer ladle nozzle wear, ladle number, ladle wear, operator number and melt chemical composition (Al, C, Mn and Si) were taken into account for the prediction of ladle nozzle opening. The best genetically developed model for ladle nozzle opening prediction correctly predicts 107 out of 115 situations of opening the ladle. The results of the genetic programming based modeling have been used in practice for the changing of several steelmaking technologies.


Journal Issues 1-3 in 2013 are accessible for free
download pdf
@article(kova13ladl,
author = "Kovacic, Miha;Jurjovec, Beno;Krajnc, Luka",
title = "Ladle nozzle opening and genetic programming",
journal = "Computer Methods in Materials Science",
volume = "13",
address = "University of Nova Gorica , Nova Gorica, SVN",
pages = "147-152",
year = "2013",
url = "www.cmms.agh.edu.pl/abstract.php?p_id=424"}