A data mining method applied to a metallurgical process

The processes in metallurgical industry are often extremely complex and measurements from their interior are scarce due to hostile (high temperatures and pressure, as well as very erosive) conditions. Still, today's constraints on high productivity and minor impact on the environment require that the processes be strictly controlled. Mathematical models can play a central role in achieving these goals. In cases where it is not possible, or economically feasible, to develop a mechanistic model of a process, an alternative is to use a data-driven approach, where a black-box model is built on historical process data. Feedforward neural networks have become popular modeling tools for this purpose, but the selection of relevant inputs and appropriate network structure are still challenging tasks. The work presented in this paper tackles these problems in the development of a model of the silicon content in hot metal produced in the ironmaking blast furnace. A pruning method is applied to find relevant inputs and their time lags, as well as an appropriate network connectivity, for solving the time-series problem at hand. In applying the model, an on-line learning of the upper-layer weights is proposed to adapt the model to changes in the input-output relations. The findings of the analysis show results in good agreement with practical metallurgical knowledge and demonstrate the feasibility of the approach.