Intelligent Control of Fused Magnesium Furnaces with Neural Network and Rule Based-Reasoning

Abstract:

The smelting process of fused magnesium furnace is a huge energy consuming process with nonlinear, current coupling and boundary conditions fluctuation. The smelting process stability is guaranteed by adjusting the three-phase electrode currents to achieve the control objective. In the past, the adjustment of electrode currents are manual control completely and the control effect is very poor, the currents fluctuation is very huge which lead to the instability of the product quality and great energy waste. As such, an intelligent control system is developed for fused magnesium furnace based on neural network (NN) algorithms and rule-based reasoning (RBR). The control objective for system is to reduce the energy consumption as much as possible under the constraint of insuring the product quality. The industrial application shows the validity and effectiveness of the proposed system.

• Periodical: Advanced Materials Research (Volume 462)
• Pages: 873-880
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.462.873
• Online since: February 2012
• Authors: Zhi Wei Wu, Chao Wang, Yong Jian Wu, Tian You Chai
• Keywords: Fused Magnesium Furnace, Intelligent Control, Neural Network (NN), Rule-Based Reasoning

References

[1] Hao Xiaohong, Wang Qingpeng, Research on intelligent control system of carbide electric arc furnace(CEAF), Proceedings of the14th World Congress of International Federation of Automatic Control, 1999, p.427～431.

DOI: 10.1109/wcica.2000.860011

[2] Liu Xiaohe, Li Jie, Adaptive reference model tracking control of electrode systems of arc furnace, Proceedings of the 4th World Congress on Intelligent Control and Automation, 2002, p.1399～1403.

DOI: 10.1109/wcica.2002.1020811

[3] Y. P. Tong, X. Zhang, and H. G. Zhang, Analysis of Optimal Operation about Purifying Magnesium Oxide Three-phase AC Electric Smelting Furnace, Control Engineering of China, 2007, 14(2): 205～ 211.

[4] G. Liu, Analysis of Work about Smelting Furnace Making MgO, Industrial Heating, 2003, 32(1): 41～43.

[5] Z. Y. Wang, Intelligent Control System of Electric Melting Magnesia, M.A. dissertation, Shenyang: Northeastern University, (2001).

[6] Ge Wei. Measuring system based on virtual instruments for arc furnace smelting MgO. M.A. dissertation, Dalian: Dalian University of Technology, (2005).

[7] G. Liu, and Y. Liu, Analysis of Couples in the Three-phase Current About Smelting Furnace Making MgO, Industrial Heating, 2004, 33(6): 55～58.

[8] Guo Maoxian. Industry Furnace, Beijing : Metallurgical Industry Press , (2002).

[9] Li Zhan-ming, A rule based human-like intelligent control method for electrical arc furnace，Proceedings of the World Congress on Intelligent Control and Automation (WCICA), 2000, p.464～466.

DOI: 10.1109/wcica.2000.860009

[10] N. Arshadi, I. Jurisica. Data mining for case-based reasoning in high-dimensional biological domains, IEEE Transactions on Knowledge and Data Engineering, 2005, 17(8): 1127～1137.

DOI: 10.1109/tkde.2005.124

[11] P. Cunningham, A Taxonomy of Similarity Mechanisms for Case-Based Reasoning, IEEE Transactions on Knowledge and Data Engineering, 2009, 21(11): 1532～1543.

DOI: 10.1109/tkde.2008.227

[12] B. Smyth, M.T. Keane, P. Cunningham, Hierarchical case-based reasoning integrating case-based and decompositional problem-solving techniques for plant-control software design, IEEE Transactions on Knowledge and Data Engineering, 2001, 13(5): 793～812.

DOI: 10.1109/69.956101

[13] N. Cercone, An. Aijun, C. Christine, Rule-induction and case-based reasoning: hybrid architectures appear advantageous, IEEE Transactions on Knowledge and Data Engineering, 2001, 11(1): 166～174.

DOI: 10.1109/69.755625

[14] D. C. Psichogios, L. H. Ungar, A hybrid neural network-first principles approach to process modeling, AICHE JOURNAL, 1992, 38(10): 1499～1511.

DOI: 10.1002/aic.690381003

[15] C. C. Ku and K. Y. Lee, Diagonal recurrent neural networks for dynamic system control, IEEE transactions on neural networks, 1993, 6(1): 144～156.

DOI: 10.1109/72.363441