论文信息 - Prediction of the hot metal silicon content in the Blast Furnace

Prediction of the hot metal silicon content in the Blast Furnace

Transforming of raw iron ore to liquid hot metal is operated at blast furnace which is one of the main unit of integrated iron and steel factories. Silicon content of liquid hot metal is the most important parameter concerning of product quality and blast furnace thermal condition. In this study a prediction model is established with artificial neural network's multilayer perceptron module by using 564 heat data of Iskenderun Iron & Steel Plant (ISDEMIR) Blast Furnace No 3. The silicon content of the next heat is predicted with accuracy of 83%.

Cigdem Inan Aci | Ahmet Beskardes | Soner Turkoglu

[1] Ling Zhuang,et al. Prediction of silicon content in hot metal using support vector regression based on chaos particle swarm optimization , 2009, Expert Syst. Appl..

[2] Hong Wang,et al. Data-Driven Dynamic Modeling for Prediction of Molten Iron Silicon Content Using ELM with Self-Feedback , 2015 .

[3] Yikang Wang,et al. Prediction of Silicon Content in Hot Metal Based on the Combined Model of EMD and SVM , 2008, 2008 Second International Symposium on Intelligent Information Technology Application.

[4] Lin Shi,et al. Model of Hot Metal Silicon Content in Blast Furnace Based on Principal Component Analysis Application and Partial Least Square , 2011 .

[5] Jian Chen,et al. A predictive system for blast furnaces by integrating a neural network with qualitative analysis , 2001 .

[6] D. Signorini,et al. Neural networks , 1995, The Lancet.

[7] Yikang Wang,et al. Prediction of Silicon Content in Hot Metal Based on SVM and Mutual Information for Feature Selection , 2011 .

[8] Abdul Rahman Mohamed,et al. Neural networks for the identification and control of blast furnace hot metal quality , 2000 .