Intelligent breakout prediction method based on support vector machine

Abstract

Breakout is a serious accident during continuous casting. In order to reduce breakout accident, a breakout prediction method was proposed based on support vector machine model. The typical characteristics of continuous casting breakout were reconstructed by thermocouple temperature signals. The temperature data of three adjacent thermocouples in the first row were added and then connected with the temperature data of the middle second row, which was used to capture the typical spatial characteristics of breakout. The 80% of true and false breakout samples were used to train the support vector machine model and 20% samples were used to test the model. The results show that this method can predict all breakouts, which has a true-sticker alarm rate of 100%. There is one false alarm and the accuracy rate is 95.8%.