A New Operational Pattern Optimization Method and Its Application in Nonferrous Metallurgy

Abstract:

Considering the difficulties of optimizing the operational parameters of the nonferrous metallurgical process, a new operational pattern optimization method is proposed, which introduces product quality and energy consumption index. Principle Component Analysis (PCA) is used to simplify the operational patterns, reduces the data dimension and overcomes the low efficiency of the operational patterns caused by huge pattern database. After the attribute reduction of PCA, the weighted attribute coefficient of the new variable is solved and a new hybrid similarity calculation method is presented, which greatly improves the speed and accuracy of pattern matching. When the pattern is reused, each matched pattern weight can be identified according to the energy consumption, which is helpful to lower the energy consumption of the nonferrous metallurgical process. Simulated experiments are carried out in terms of the real production data. The Simulated results indicate that this novel method is a promising and effective technology to be applied to the real industrial process to reduce the zinc dust consumption and increase the qualified rate of the outlet cobalt ions.

• Periodical: Advanced Materials Research (Volumes 690-693)
• Pages: 3194-3198
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.690-693.3194
• Online since: May 2013
• Authors: Tie Bin Wu, Yun Cheng, Hong Qiu Zhu, Yong Gang Li, Zhi Kun Hu
• Keywords: Energy Consumption (EC), Nonferrous Metallurgy, Operational Pattern, Principal Component Analysis (PCA)

References

[1] A. Kontopoulos, K. Krallis, E. Koukourakis. Hybrid knowledge-based system as a process control tool for improved energy efficiency in alumina calcining furnaces. Applied Thermal Engineering, Vol. 17(2010), p.935

DOI: 10.1016/s1359-4311(96)00078-6

[2] W.H,Gui, C.H. Yang, Y.G.,Li, et al. Data- driven Operational-pattern Optimization for Copper Flash Smelting Process[J]. Acta Automatica Sinica, Vol. 35(2009), p.718

DOI: 10.3724/sp.j.1004.2009.00717

[3] B.,Qiao, Y.R.,Li, P.,Jiang. Hierarchical reduction approach of the rough sets theory and its basis on the information theory. IEEE International Conference on Systems, Man and Cybernetics, Vol. 7(2002)

DOI: 10.1109/icsmc.2002.1175675

[4] P.C. Chang, C.H. Liu, R.K. Lai. A fuzzy case-based reasoning model for sales forecasting in print circuit board industries. Expert Systems with Applications, Vol.34(2008), p.(2049)

DOI: 10.1016/j.eswa.2007.02.011

[5] Q.,Tian, X. Zhu. Statistics Analysis of PCA-Based Sensor Fault Detection[J]. Applied Mechanics and Materials. Vol.121(2011), p.1085

DOI: 10.4028/www.scientific.net/amm.121-126.1085

[6] J.,Wang, S.T. Wang,, Z.H., Deng.Survey on challenges in clustering analysis research[J]. Control and Decision, Vol.21(2011), p.321