Multi-objective intelligent coordinating optimization blending system based on qualitative and quantitative synthetic model

Abstract

A multi-objective intelligent coordinating optimization strategy based on qualitative and quantitative synthetic model for Pb-Zn sintering blending process was proposed to obtain optimal mixture ratio. The mechanism and neural network quantitative models for predicting compositions and rule models for expert reasoning were constructed based on statistical data and empirical knowledge. An expert reasoning method based on these models were proposed to solve blending optimization problem, including multi-objective optimization for the first blending process and area optimization for the second blending process, and to determine optimal mixture ratio which will meet the requirement of intelligent coordination. The results show that the qualified rates of agglomerate Pb, Zn and S compositions are increased by 7.1%, 6.5% and 6.9%, respectively, and the fluctuation of sintering permeability is reduced by 7.0%, which effectively stabilizes the agglomerate compositions and the permeability.

Keywords

Pb-Zn sintering blending process / qualitative and quantitative synthetic model / multi-objective optimization / area optimization / intelligent coordination

References

[1] XiaDe-hong, ZhangGang. Simulation of thermal process of sintering[J]. Energy for Metallurgical Industry, 2004, 23(4): 10-13(in Chinese)

[2] JiaJuan-yu, BaiChen-guang, LaiHong, et al.. Optimization and realization for sinter and ore blending for blast furnace[J]. Journal of Chongqing University: Natural Science, 2002, 25(10): 68-71(in Chinese)

[3] YangDong-jin, ChenJi-guo, YuZhong-nian, et al.. Optimization of mix proportioning, sintering and pelletizing[J]. Sintering and Pelletizing, 2000, 25(1): 14-17(in Chinese)

[4] LiangZhong-yu, HuLin, DengNeng-yun, et al.. Analysis of sinter charge proportioning by linear optimization[J]. Iron and Steel, 2001, 36(10): 12-13(in Chinese)

[5] EfsathiouJExpert systems in process control[M], 1989, Essex, Longman

[6] HaganM T, DemuthH B, BealeM HNeural network design[M], 1996, Boston, PWS Publishing

[7] WuMin, NakanoM, SheJin-hua. A model-based expert control strategy using neural network for the coal blending process in an iron and steel plant[J]. Expert Systems with Application, 1999, 16(3): 271-281

[8] YangChun-hua, ShenDe-yao, WuMin, et al.. Synthesis of qualitative and quantitative methods in a coal blending expert system for coke oven[J]. Acta Automatica Sinica, 2000, 26(2): 226-232(in Chinese)

[9] WangYa-linStudy on intelligent integrated modeling theory and its applications to optimal control of nonferrous metallurgical process [D], 2001, Changsha, School of Information Science and Engineering, Central South University(in Chinese)

[10] WangYi-wen, GuiWei-hua, WangYa-lin. Integrated model for predicting burning through point of sintering process based on optimal combination algorithm[J]. The Chinese Journal of Nonferrous Metals, 2002, 12(1): 191-195(in Chinese)

[11] ChenXiao-fang, GuiWei-hua, WangYa-lin, et al.. Soft-sensing model of sulfur content in agglomerate based on intelligent integrated strategy, Softsensing model of sulfur content in agglomerate based on intelligent integrated strategy[J]. Control Theory and Applications, 2004, 21(1): 75-80(in Chinese)

[12] WangYa-lin, GuiWei-hua, YangChun-hua, et al.. Prediction for composition of Pb-Zn agglomerate based on integrated modeling[J]. Journal of Central South University: Science and Technology, 2005, 36(1): 113-118(in Chinese)