Improved SVM Model for Predicting Pellet Metallurgical Properties Based on Textural Characteristics

From the point of view that pellet microstructure determines its metallurgical properties, an improved support vector machine (SVM) model for properties forecast is studied based on mineral phase characteristics, in order to improve evaluation efficiency properties. The composed a SVM with self-adaptive selection kernel parameters and compounding types. This not only guarantees super interpolation ability model, but also takes into account good generalization performance. Based 200 sets original sample information, quantitative relationship between main characteristics grade labels (reduction expansion index RSI, reduction RI, low temperature pulverization RDI) was determined by model. With simulation results RDI accuracy 100%, 98%, 100% respectively, precise realized.