Sampling Strategy of Bubble Characteristics in a 1:2 Scale Curved Continuous Casting Mold: Parametric and Prediction Study

Argon gas injection in slab continuous casting is common practice to counter SEN clogging phenomena. Bubble characteristics determine the probability of bubble-driven defects such as steel cleanliness, liquid steel reoxidation, and sliver and blister defects. 1:2 scaled water model studies were performed with the help of an advanced high-speed-high-resolution camera shadowgraph imaging technique. Bubble Sauter mean diameter and count were calculated using Trainable Weka segmentation, a machine learning image-based segmentation in the ImageJ platform for different processing conditions such as gas flow rate, liquid flow rate, mold width, and submerged entry nozzle (SEN) depth. A predictive model was developed on the experimental data using an artificial neural network (ANN) algorithm to optimize the bubble mean diameter and count sampling strategy. The model performance is optimized based on the cross-validated adjusted R2. The model shows significant promise with bootstrapping aggregation, five-fold cross-validation, and improved accuracy.