In regions rich in iron ore and high ash non-coking coal quite often the preferred technology of steelmaking is the Rotary Kiln - Electric Arc Furnace route, as the minimum capacity level is of the order of hundred thousand tones and required investment is substantially less. The difference can be in the cost of production due the huge power requirement in electric steelmaking. Direct Reduced Iron (DRI) is produced in a rotary kiln and this route is commonly known as the DRI-EAF route.

In a rotary kiln the achievement of desired product quality depends upon the controlled addition of coal and air for developing the right reducing atmosphere for producing DRI of 90% metallization. DRI being a result of reduction of iron ore the production quantity and metallic iron content are conflicting i.e increasing the value of one will in principle reduce the value of the other. As both these objectives are simultaneously equally important they must be simultaneously optimized using multi-objective optimization techniques.

Multi-objective optimization facilitates the handling of data using constraints and one of the best ways to handle data with constraints is using genetic algorithms as the search space in this study is not very well defined. Genetic algorithms provide for a robust method of handling the data. The relationship between the individual inputs, a set of several variables like iron ore, coal and air input rate, ore and coal quality with the two simultaneous outputs, DRI production quantity and FeM content of DRI have been developed using artificial neural networks in this study while the search for simultaneous optimum results has been done using genetic algorithms to generate the input values of operating parameters and the corresponding output values.

Some typical results are presented in the attached Figure.

• Legal notice:
  

  Copyright (c) Pielaszek Research, all rights reserved.
  The above materials, including auxiliary resources, are subject to Publisher's copyright and the Author(s) intellectual rights. Without limiting Author(s) rights under respective Copyright Transfer Agreement, no part of the above documents may be reproduced without the express written permission of Pielaszek Research, the Publisher. Express permission from the Author(s) is required to use the above materials for academic purposes, such as lectures or scientific presentations.
  In every case, proper references including Author(s) name(s) and URL of this webpage: https://science24.com/paper/10749 must be provided.

1. Genetic algorithms: Explanation of basic ideas (tutorial lecture part I)
2. Genetic algorithms: Multi-objective methods (tutorial lecture part II)
3. Tailor-made material design: An evolutionary approach using multi-objective genetic algorithms
4. The genetic algorithm-neural net combination (tutorial lecture part III)
5. Genetic algorithm based search on the role of variables in the work hardening process of multiphase steels
6. Modeling of recrystallization in cold rolled copper using inverse cellular automata and genetic algorithms