The end point forecast of carbon value based on wavelet neural network

Author

Wang, Dongmei ; You, Wen

Author_Institution

Inst. of Electr. & Electron. Eng., Changchun Univ. of Technol., Changchun, China

Volume

4

fYear

2010

fDate

24-26 Aug. 2010

Firstpage

225

Lastpage

227

Abstract

Carbon value online measurement is one of the most important tasks of the AOD furnace ferroalloy production process. Being the smelting process is complex in this paper promote the wavelet neural network algorithm in order to predict the endpoint of carbon value and using online data to training the wavelet neural network. The simulation results showed that the prediction relative error between the prediction and the practical value is within ± 5% and the convergence rate of the learning algorithm is fast.

Keywords

carbon; iron alloys; learning (artificial intelligence); metallurgical industries; neural nets; smelting; wavelet transforms; AOD furnace ferroalloy production process; carbon value online measurement; end point forecast; learning algorithm; prediction relative error; smelting process; wavelet neural network algorithm; Artificial neural networks; Helium; Wavelet analysis; Carbon Value; Forecast Model; Furnace Gas Analysis; Neural Network; Wavelet;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer, Mechatronics, Control and Electronic Engineering (CMCE), 2010 International Conference on

Conference_Location

Changchun

Print_ISBN

978-1-4244-7957-3

Type

conf

DOI

10.1109/CMCE.2010.5610163

Filename

5610163