Optimization Research on Converter Steelmaking Process Parameters Based on DOE
| Autor: | Yu Kai Li, Bi Hong Lu, Bao Zhang Qu |
|---|---|
| Rok vydání: | 2013 |
| Předmět: |
Engineering
Artificial neural network business.industry Mechanical Engineering Mean squared prediction error Process (computing) Mechanical engineering chemistry.chemical_element Scrap Steelmaking chemistry Mechanics of Materials Effective method General Materials Science Statistical analysis business Process engineering Carbon |
| Zdroj: | Key Engineering Materials. :128-132 |
| ISSN: | 1662-9795 |
| Popis: | The temperature and carbon content at blow end point should be controlled strictly during the BOF converter steelmaking process. Meanwhile many factors have impact on the temperature and carbon content at blow end point. These factors include initial weight of molten iron, initial weight of scrap steel, oxygen blow duration, the temperature and carbon content when lowering the sublance, as well as the weight of all kinds of addition reagents. In order to determine the optimized process parameters so as to reach the ideal temperature and carbon content at blow end point, this paper built a series of experiment programs based on DOE. According to the experiment programs, authors conducted these experiments with the help of RBF neural network and analyzed each parameters as well as some interactions impact on target. According to the statistical analysis results of experiment data (the SNR), authors extract significant factors and reached an optimized process parameters A3B3C2D1E1F3G2H3J2. According to the RBF neural network, the prediction error of carbon content and temperature is only 0.0063 and 0.0159 respectively. The result proves that DOE is an effective method in optimizing process parameters, and worth promoting and applying in converter steelmaking process. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|