C-Mn yield forecasting model based on SVM. Issue 2 (May 2021)

• Record Type: Journal Article
• Authors: Li, Jinghang; Bai, Juanli; Yu, Bozhong
• Is Part Of: IOP conference series. Volume 781:Issue 2(2021)
• Publication Date: 2021-05
• Subjects: ARIMA -- SVM; Earth sciences -- Periodicals; Environmental sciences -- Congresses; Environmental sciences -- Periodicals; 550.5
• DOI: 10.1088/1755-1315/781/2/022024
• Languages: English
• ISSNs: 1755-1307

Abstract

Abstract: With the rapid development of economy, how to increase steel output and reduce plant cost is of great significance. Deoxy alloying is an important link in iron and steel smelting. This paper aims at the optimization of the burdening scheme of deoxy alloying of molten steel. The aim is to establish the SVM optimization model based on the data and predict the yield of C/Mn. First of all, we established a time series model based on the obtained results of the problem and the furnace times as the time, and used the ARIMA time series method in SPSS software to predict the yield of C/Mn. Secondly, we improve the model, use the historical data to train and forecast the support vector machine model (SVM), and compare the predicted values of the SVM model and the time series model, and get the conclusion that the SVM model is more accurate than the time series model.