An Intelligent Integrated Method for Quality Prediction in Lead-Zinc Sintering Process

Abstract:

Based on some features in lead-zinc sintering process (LZSP), such as large time delay and strong non-linearity, an intelligent integrated method for quality prediction based on back-propagation neural network (BPNN) and improved grey system (IGS) is presented. First, the compositions of agglomerate are predicted by BPNN and IGS models. Then, a recursive entropy algorithm for the weighting coefficients is devised from the viewpoint of the information theory and an intelligent integrated prediction model (IIPM) is established. The compositions of sinter agglomerate are predicted by integrating the two prediction models. Application results show that the IIPM has higher prediction precision than that of single model and the proposed intelligent integrated method settles the modeling problem of the quality in the LZSP.

• Periodical: Applied Mechanics and Materials (Volumes 52-54)
• Pages: 674-679
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.52-54.674
• Online since: March 2011
• Authors: Chun Sheng Wang, Min Wu, Qi Lei
• Keywords: BP Neural Network (BPNN), Grey System, Information Entropy, Lead-Zinc Sintering Process

References

[1] J. R. Siemon, E. Kowalczyk, D. P. Fitzgibbons, and W. Baguley: Peak bed temperature prediction on a lead/zinc sinter plant, Minerals Engineering, Vol. 4, no. 1 (1991), pp.63-78.

DOI: 10.1016/0892-6875(91)90119-g

[2] G. S. Upadhyaya: Some issues in sintering science and technology, Materials chemistry and physics, Vol. 67 (2001), pp.1-5.

[3] S. H. Lee, C. B. Yoon, S. M. Lee, and H. E. Kim: Reaction sintering of lead zinc niobate-lead zirconate titanate ceramics, Journal of the European Ceramic Society, Vol. 38, no. 6 (2003), pp.1081-1090.

DOI: 10.1016/j.jeurceramsoc.2004.10.005

[4] E. Jak, B. J. Zhao, I. Harvey, and P. C. Hayes: Experimental study of phase equilibria in the PbO-ZnO-Fe2O3-(CaO+SiO2) system in air for the lead and zinc blast furnace sinters (CaO/SiO2 weight ratio of 0. 933 and PbO/CaO+SiO2) ratios of 2. 0 and 3. 2), Metallurgical and Materials Transactions B: Process Metallurgy and Materials Processing Science, Vol. 34, no. 4 (2003).

DOI: 10.1007/s11663-003-0065-2

[5] Y. L. Wang, C. H. Yang, W. H. Gui and X. Ling: Hierachical intelligent optimization blending system based on production indices for lead-zinc sintering process, In the 17th IFAC World Congress, Seoul, Korea (2008), pp.3286-3291.

DOI: 10.3182/20080706-5-kr-1001.00558

[6] M. J. Er, J. Liao and J. Y. Lin: Fuzzy neural network-based quality prediction system for sintering process, IEEE Transactions on Fuzzy Systems, Vol. 8, no. 3 (2000), pp.314-324.

DOI: 10.1109/91.855919

[7] C. H. Xu, M. Wu, J. H. She and R. Yokoyama: Integrated neural-network-based method for predicting synthetic permeability in lead-zinc sintering process, In the 7th IEEE International Conference on Cybernetic Intelligent Systems, London, UK (2008).

DOI: 10.1109/ukricis.2008.4798973

[8] C. S. Wang and M. Wu: Intelligent integrated predictive model for BTP in lead-zinc sintering process, Journal of Engineering Systems Modelling and Simulation, Vol. 2, no. 3 (2010), pp.162-168.

DOI: 10.1504/ijesms.2010.035111

[9] Y. H. Lin and P. C. Lee: Novel high-precision grey forecasting model. Automation in Construction, Vol. 16 (2007), pp.771-777.

DOI: 10.1016/j.autcon.2007.02.004

[10] W. L. Yao Albert, S. C. Chi and J. H. Chen: An improved grey-based approach for electricity demand forecasting. Electric Power Systems Research, Vol. 67 (2003), pp.217-224.

DOI: 10.1016/s0378-7796(03)00112-3

[11] P. Themis, K. Nick and M. Alberto: Using datacube aggregate for approximate querying and deviation detection. IEEE Transactions on Knowledge and Data Engineering, Vol. 17, no. 11 (2005), pp.1465-1477.

DOI: 10.1109/tkde.2005.187

[12] Mohamed Saleh: Estimating market shares in each market segment using the information entropy concept. Applied Mathematics and Computation, Vol. 190 (2007), pp.1735-1739.

DOI: 10.1016/j.amc.2007.02.049