Multi-sensor Stockline Tracking within a Blast Furnace

摘要

The paper presents a synergistic approach for height tracking within a blast furnace (BF). The Frequency Modulated Continuous Wave (FMCW) radar has been employed to measure the height and surface profile of the burden surface. However the radar signal is easily disturbed, by the radar anomalies, during the process of continuous measurement. The data from rotating chute and charging switch provide information on contextual relevance with radar anomalies. An anomaly detection models has been developed to increase the measurement accuracy by utilizing contextual information. The approach has been validated on real BF. The root mean squared (RMS) error in the measured height is reduced by 17% when using the proposed approach compared to the case without it. The results suggest that the proposed approach successfully adapts to changes in the pattern and characteristics of the burden surface.