Intelligent Modeling of Tuyere Raceway of Blast Furnace

A new soft measurement model of blast furnace tuyere raceway temperature is proposed. Firstly, the image data collected from the tuyere is transformed from RGB space to HSV space, and the features of the image data are extracted after non-uniform quantization. Then, the extracted image features are used as input data, the actual collected temperature data are used as sample labels for KPLS regression prediction. Aiming at the problem that KPLS parameters are not easy to adjust, GWO algorithm is introduced to optimize the parameters, which not only improves the accuracy of the algorithm, but also reduces the difficulty of parameter adjustment, so as to improve the prediction accuracy and training efficiency of the model. Finally, a large number of experiments are carried out with the actual data of a steel plant. The simulation results show that this method can predict the temperature with high accuracy, which shows that this method has good practicability and accuracy.