PREDICTION MODEL OF MAGNESIUM POWDER CONSUMPTION DURING HOT METAL DURING HOT METAL PRE-DESULFURIZATION

摘要

Based on the productive practice of a steel plant, adopted the back propagation (BP) algorithm with the network configuration of 4-12-1 and the range of normalization from 0 to 1, used Visual Basic 6.0 software, the prediction model of magnesium powder consumption during hot metal pre-desulfurization processing was established. Meanwhile, four parameters, which are the weight and temperature of hot metal, the initial and final sulfur content in hot metal, were selected as input parameters. The data of 210 heats were used as the training samples and the other 46 heats were randomly selected as the test samples. The results show that the prediction errors of magnesium powder consumption less than ±5 kg and ±10 kg are 54.3 percent and 89.1 percent of the total test heats respectively. Average absolute error is 5.12 kg. Minimum absolute error is 0.02 kg. The model greatly coincides with the actual production operation.