基于粒度分布评估与优化的制粒过程 PSO-BP 控制算法

李勇; 吴敏; 曹卫华; 赖旭芝; 王春生

doi:10.3724/SP.J.1004.2012.01007

基于粒度分布评估与优化的制粒过程 PSO-BP 控制算法

doi: 10.3724/SP.J.1004.2012.01007

李勇^1,2,
吴敏^1,2,,
曹卫华^1,2,
赖旭芝^1,2,
王春生^1,2

1.
中南大学信息科学与工程学院长沙 410083;
2.
先进控制与智能自动化湖南省工程实验室长沙 410083

详细信息

通讯作者:
吴敏,中南大学信息科学与工程学院教授.1999年获东京工业大学博士学位.主要研究方向为过程控制,鲁棒控制,智能系统.

计量
- 文章访问数: 1987
- HTML全文浏览量: 45
- PDF下载量: 1131
- 被引次数: 0
出版历程
- 收稿日期: 2011-05-06
- 修回日期: 2012-03-20
- 刊出日期: 2012-06-20

PSO-BP Control Algorithm of Granulation Process Based on Evaluation and Optimization of Granularity Distribution

LI Yong^1,2,
WU Min^{1,2
,},
CAO Wei-Hua^1,2,
LAI Xu-Zhi^1,2,
WANG Chun-Sheng^1,2

1.
School of Information Science and Engineering, Central South University, Changsha 410083;
2.
Hunan Engineering Laboratory for Advanced Control and Intelligent Automation, Changsha 410083

摘要

摘要: 针对钢铁烧结中混合料粒度分布无法在线测量、难以实现混合制粒过程优化控制的问题,提出基于粒度分布评估函数(Evaluation model of granularity distribution, EMGD)的混合制粒优化控制算法. 首先,根据烧结生产历史数据和混合料筛分实验数据建立粒度分布BP神经网络(BP neural network, BPNN)评估模型; 然后,以该模型为目标函数,以制粒过程状态参数的边界为约束条件,采用粒子群算法(Particle swarms optimization, PSO)计算粒度分布优化值; 最后建立基于BPNN的制粒水分设定模型,根据粒度分布优化值和当前配重实现水分优化控制. 仿真实验和工业应用表明评估模型真实反映了粒度分布对料层透气性的影响; PSO-BP粒度分布优化控制算法对改善透气性、减少燃料损耗、稳顺烧结生产具有重要意义.
- 烧结混合制粒 /
- 粒度分布评估函数 /
- BP神经网络 /
- 粒子群算法
Abstract: Since granularity distribution of mixing materials in iron sintering can hardly be measured and controlled online, an optimal control algorithm based on evaluation model of granularity distribution (EMGD) has been developed. Firstly, EMGD based on BP neural network (BPNN) has been built by studying data from screening tests and historical state parameters in sintering process. Secondly, by using particle swarms optimization (PSO), optimal granularity distribution can be found from the optimization model restricted by the boundaries of state parameters, whose objective function is EMGD. Finally, according to optimal granularity distribution and online solid flow measurement, humidity setting model based on BPNN is studied to keep the granularity distribution stable and reasonable. Simulation and industrial application have proven that the algorithm makes great sense in permeability improvement, reduction of fuel consumption and stability of sintering process.
- Granulation /
- evaluation model of granularity distribution (EMGD) /
- BP neural network (BPNN) /
- particle swarms optimization (PSO)

HTML全文

参考文献(1)

[1]

Wang Jing-Bo, Wu Feng-Xia, Li Fa-Zhan. Some measures for reducing sinter returns. Sintering and Pelletizing, 2003, 28(4): 53-55(王静波, 吴凤霞, 李发展. 降低烧结返矿率的途径与实践. 烧结球团, 2003, 28(4): 53-55)[2] Li Qiang. Research on the granulation parameters of sinter mix with higher concentrates ratio in TAIGANG. Sintering and Pelletizing, 2008, 33(4): 24-28(李强. 太钢高精粉率原料条件下制粒参数优化的探索. 烧结球团, 2008, 33(4): 24-28)[3] Li Yong, Wu Min, Cao Wei-Hua. An adaptive control scheme for granulating humidity craft using PSO algorithm. Chinese Journal of Scientific Instrument, 2009, 30(6S): 64-68 (李勇, 吴敏, 曹卫华. 基于PSO算法的烧结制粒湿度自适应控制. 仪器仪表学报, 2009, 30(6S): 64-68)[4] Hossein-Babaei F, Rahbarpour S. Porosity modification for the adjustment of the dynamic range of ceramic humidity sensors. In: Proceedings of the 3rd International Conference on Sensing Technology. Tainan, China: IEEE, 2008. 648-651[5] Gong Da-Cheng, Xiang Zhan-Qin, Pan Xiao-Hong, Lv Fu-Zai. Design and research of in-process particle size measurer. Chinese Journal of Scientific Instrument, 2006, 27(6): 602-606, 642 (龚大成, 项占琴, 潘晓弘, 吕福在. 新型在线粒度检测仪的设计与研究. 仪器仪表学报, 2006, 27(6): 602-606, 642)[6] Waters A G, Litster J D, Nicol S K. A mathematical model for the prediction of granule size distribution for multicomponent sinter feed. The Iron and Steel Institute of Japan International, 1989, 29(4): 274-283[7] Kapur P C, Runkana V. Balling and granulation kinetics revisited. International Journal of Mineral Processing, 2003, 72(1-4): 417-427[8] Kawaguchi T, Yoshinaga M, Ichidate M. Development and application of an integrated simulation model for iron ore sintering. Ironmaking Proceedings, 1987, 46(1): 99-106[9] Zhou Chuan-Qiang, Bai Chen-Guang, Lv Xue-Wei, Xie Hao, Wang Tao, Xia Hai-Ying. Fuzzy cluster analysis of granulation characteristics of iron ore. Sintering and Pelletizing, 2009, 34(3): 16-20 (周传强, 白晨光, 吕学伟, 谢皓, 王涛, 夏海英. 铁矿粉制粒特性模糊聚类分析. 烧结球团, 2009, 34(3): 16-20)[10] Li Ming, Zhang Hua-Guang, Wang Cheng-Hong. Fuzzy tracking control design for nonlinear systems via T-S fuzzy performance evaluator. Acta Automatica Sinica, 2004, 30(4): 578-582 (黎明, 张化光, 王成红. 基于T-S模糊性能评估器的非线性系统跟踪控制器设计. 自动化学报, 2004, 30(4): 578-582)[11] Ge T. The concept of configuration redundancy and integrated evaluation and disposition of redundancy in sensor systems. Acta Automatica Sinica, 2003, 29(2): 181-189[12] Wu Min, Tang Zhao-Hui. Expert control using neural networks for an electrolytic zinc process. Acta Automatica Sinica, 2001, 27(6): 867-869(吴敏, 唐朝晖. 锌湿法冶炼电解过程的神经网络专家控制. 自动化学报, 2001, 27(6): 867-869)[13] Cai Z X. Intelligent Control. Beijing: Publishing House of Electronics Industry, 2004. 253-258[14] Wu Min, Xu Chen-Hua. An intelligent integrated predictive method based on gas temperature profile for Burn-through Point. Acta Automatica Sinica, 2007, 33(12): 1313-1320 (吴敏, 徐辰华. 基于烟气温度场分布的烧穿点智能集成预测方法. 自动化学报, 2007, 33(12): 1313-1320)[15] Pan Feng, Chen Jie, Xin Bin, Zhang Juan. Several characteristics analysis of particle swarm optimizer. Acta Automatica Sinica, 2009, 35(7): 1010-1015 (潘峰, 陈杰, 辛斌, 张娟. 粒子群优化方法若干特性分析. 自动化学报, 2009, 35(7): 1010-1015)

施引文献

资源附件(0)

访问统计