A Prediction Model for Tumbler Strength Based on Deep Temporal Clustering Across Multiple Operating Conditions

Iron ore sintering is a critical step in the blast furnace ironmaking process and tumbler strength is a key physical parameter for evaluating sintered ore quality. Accurate prediction of tumbler strength aids in adjusting process parameters to ensure high strength and stability, fulfilling the blast furnace's needs. This paper proposes a tumbler strength prediction model based on deep temporal clustering in multiple work modes. First, work modes are identified using feature space mapping and deep clustering techniques, addressing the limitations of traditional clustering methods in condition identification. Next, a spatio-temporal modeling approach is applied to independently model each work mode, considering the spatio-temporal characteristics of the sintering process. To mitigate the impact of sample size imbalances across work modes, a weighted strategy is introduced, assigning different weights to data from each condition. Experimental results show that the proposed method achieves high prediction accuracy for tumbler strength.