Neural networks for the identification and control of blast furnace hot metal quality

The operation and control of blast furnaces poses a great challenge because of the difficult measurement and control problems associated with the unit . The measurement of hot metal composition with respect to silica and sulfu r are critical to the economic operation of blast furnaces. The measurement of the compositions require spectrographic techniques which can be perform ed only off line. An alternate technique for measuring these variables is a Soft Sensor based on neural networks. In the present work a neural network based model has been developed and trained relating the output variables w ith a set of thirty three process variables. The output variables include t he quantity of the hot metal and slag as well as their composition with res pect to all the important constituents. These process variables can be meas ured on-line and hence the soft sensor can be used on-line to predict the o utput parameters. The soft sensor has been able to predict the variables wi th an error less than 3%. A supervisory control system based on the neural network estimator and an expert system has been found to substantially impr ove the hot metal quality with respect to silicon and sulfur. (C) 2000 Else vier Science Ltd. All rights reserved.