Control Process optimization of Vacuum Salt Based on SVM

摘要

For the optimization of vacuum salt control process, the SVM learning algorithm is used to realize the key solid-liquid ratio prediction, so that the control parameters can be adjusted in advance to optimize the production process. Filter a large number of features by using custom filter and wrap feature selection. The RBF (Radial Basis Function) kernel function in SVM is selected for training to construct a model for predicting the ratio of solid to liquid. The experimental results show that the accuracy of the prediction of 297,541 data is over 80%, and the overall average error is less than 15%.