Converter end-point prediction model using spectrum image analysis and improved neural network algorithm

• Autorzy: Wen H. Y. , Zhao Q. , Chen Y. R. , Zhou M. C. , Zhang M. , Xu L. F.
• Języki publikacji: EN

Abstrakty

EN

Aiming at the present situation of the steelmaking end-point control at home and abroad, a neural network model was established to judge the end-point. Based on the colour space conversion and the fiber spectrum division multiplexing technology, a converter radiation multi-frequency information acquisition system was designed to analyze the spectrum light and image characteristic information, and the results indicate that they are similar at early-middle stage but dissimilar when approach the steelmaking blowing end. The model was trained and forecasted by using an improved neural network correction coefficient algorithm and some appropriate variables as the model parameters. The experimental results show the proposed algorithm improves the prediction accuracy by 15.4% over the conventional algorithm in 5s errors and the respond time is about 1.688s, which meets the requirements of end-point judgment online.

Słowa kluczowe

EN

spectrum; image; neural network; converter; end-point

• Wydawca: Oficyna Wydawnicza Politechniki Wrocławskiej
• Czasopismo: Optica Applicata
• Rocznik: 2008
• Tom: Vol. 38, nr 4
• Strony: 693--704
• Opis fizyczny: Bibliogr. 14 poz.,

Twórcy

autor

Wen H. Y.

autor

Zhao Q.

autor

Chen Y. R.

autor

Zhou M. C.

autor

Zhang M.

autor

Xu L. F.

• School of Electronic Engineering and Optoelectronic Technology, Nanjing University of Science & Technology, Nanjing 210094, China

Bibliografia

• [1] LIU L., Technical progress in converter steelmaking in China, Iron and Steel 40(2), 2005, pp. 1–5.
• [2] WANG M.H., HUI Z.G., Shi X.L., End-point Control Technology of Converter, Angang Technology 333(3), 2005, pp. 6–10.
• [3] MERRIMAN D., Mass spectrometry for oxygen steel-making control, Steel Times 225(11), 1997, pp. 439–40.
• [4] SHARAN A., Light sensors for BOF carbon control in low carbon heats, [In] Steelmaking Conference Proceedings, Toronto, Canada: ISS, 81, 1998, pp. 337–45.704 H.-Y.WEN et al.
• [5] SHARAN A., Fiber optic sensor and method of use thereof to determine carbon content of molten steel contained in a basic oxygen furnace, US, 6175676[P], 2001, 1–16.
• [6] WANG Y., YANG N.C., WANG C.K., Present situation and development of converter steelmaking in China, Special Steel 26(4), 2005, pp. 1–5.
• [7] YUN S.Y., CHANG K.S., Dynamic prediction using neural network for automation of BOF process in steel industry, Iron and Steelmaker 23(8), 1996, pp. 37–42.
• [8] DING R., LIU L., Artificial intelligence static control model in converter steelmaking, Iron and Steel 32(1), 1997, pp. 22–6.
• [9] XIE S.M., TAO J., Chai T.Y., BOF steelmaking endpoint control based on network, Control Theory and Applications 20(6), 2003, pp. 903–7.
• [10] WANG Z.J., CHAI T.Y., SHAO C., Slab minerature prediction model based on RBF neural network, Journal of System Simulation 11(3), 1999, pp. 181–4.
• [11] SMITH A.R., Color gamut transformation pairs, Computer Graphics, 12(3), 1978, pp. 12–9.
• [12] GONZALEZ R.C., WOODS R.E., EDDINS S.L., Digital Image Processing Using MATLAB, Shaddle River, New Jersey, US: Prentice Hall, 2004.
• [13] CHEN K.Z., Optimized Arithmetic, Xi’an: Northwestern Polytechnic University Press, 2001.
• [14] HORNIK K., STINCHCOMBE M., WHITE H., Multilayer feedforward networks are universal approximators, Neural Network, 2(5), 1989, pp. 359–66.