Wick Sintered Temperature Forecasting Based on Support Vector Machines with Simulated Annealing

The law of sintering temperature’ changing during resistance furnace sintering is the very important technology information. Support vector machines (SVMs) have been successfully employed to solve nonlinear regression and time series problems. In order to improve time efficiency of prediction, a new sintered furnace temperature law prediction model and method based on SVM in this paper. Moreover, simulated annealing (SA) algorithms were employed to choose the hyperparameters of a SVM model. A comparison of the performance between SVM optimized by Particle Swarm Optimization (SVM-PSO) and SVM-SA is carried out. Experiments results demonstrate that SVM-SA can achieve better accuracy and generalization than the SVM-PSO. Consequently, the SVM-SA model provides a promising alternative for sintered furnace temperature law.