Paper
20 May 2009 Combining SVM and flame radiation to forecast BOF end-point
Hongyuan Wen, Qi Zhao, Lingfei Xu, Munchun Zhou, Yanru Chen
Author Affiliations +
Abstract
Because of complex reactions in Basic Oxygen Furnace (BOF) for steelmaking, the main end-point control methods of steelmaking have insurmountable difficulties. Aiming at these problems, a support vector machine (SVM) method for forecasting the BOF steelmaking end-point is presented based on flame radiation information. The basis is that the furnace flame is the performance of the carbon oxygen reaction, because the carbon oxygen reaction is the major reaction in the steelmaking furnace. The system can acquire spectrum and image data quickly in the steelmaking adverse environment. The structure of SVM and the multilayer feed-ward neural network are similar, but SVM model could overcome the inherent defects of the latter. The model is trained and forecasted by using SVM and some appropriate variables of light and image characteristic information. The model training process follows the structure risk minimum (SRM) criterion and the design parameter can be adjusted automatically according to the sampled data in the training process. Experimental results indicate that the prediction precision of the SVM model and the executive time both meet the requirements of end-point judgment online.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hongyuan Wen, Qi Zhao, Lingfei Xu, Munchun Zhou, and Yanru Chen "Combining SVM and flame radiation to forecast BOF end-point", Proc. SPIE 7283, 4th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test and Measurement Technology and Equipment, 728327 (20 May 2009); https://doi.org/10.1117/12.828702
Lens.org Logo
CITATIONS
Cited by 1 patent.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Oxygen

Data modeling

Carbon

Neural networks

Process modeling

Video

Data acquisition

RELATED CONTENT


Back to Top