Intelligent prediction method of quality for continuous casting process

Quality prediction of casting billet in continuous casting process has great significance on ensuring the continuity of production and improving the quality of casting billet. The process parameters have influence on the quality of casting billet in continuous casting process, so this paper proposes an intelligent prediction method of casting quality based on multiple process parameters. Through the analysis of the relationship between multiple process parameters and the casting quality, the casting quality prediction model based on least squares support vector machine (LSSVM) is established. And an improved particle swarm optimization (iPSO) algorithm is used to optimize the parameters of the prediction model. Then the quality prediction of casting billet under different combinations of process parameters could be implemented. In the continuous casting grade transition process, the proposed method in this paper is used to establish the prediction model of the intermixing length. The results of the case prove the effectiveness of the proposed method.