Please wait a minute...
J4  2010, Vol. 44 Issue (7): 1266-1269    DOI: 10.3785/j.issn.1008-973X.2010.07.006
自动化技术     
基于遗传规划的铁矿烧结终点2级预测模型
商秀芹, 卢建刚, 孙优贤
浙江大学 工业控制技术国家重点实验室,浙江 杭州 310027
Genetic programming based twoterm prediction model of iron ore burning through point
SHANG Xiuqin, LU Jiangang, SUN Youxian
State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China
 全文: PDF  HTML
摘要:

为了解决铁矿烧结过程中烧结终点(BTP)的建模问题,提出改进的混合分类遗传规划(CGP)算法.算法将K中心聚类算法与遗传规划(GP)相结合,通过K中心聚类算法对烧结过程工况进行分类.对每一类,采用遗传规划建立风箱温度自回归预测模型.模型为2级温度预测模型,即基于温度拐点的中期模型和临近烧结终点处的短期模型.烧结终点通过预测温度的3次曲线拟合得到.实验仿真表明了所提出的2级温度预测模型的有效性.

Abstract:

A novel classified genetic programming (CGP) algorithm was proposed to model the burning through point (BTP) in the sintering process. The algorithm integrated the Kmedoids clustering into the genetic programming (GP). The Kmedoids clustering was adopted to classify the working conditions of sintering process into K clusters. For each cluster, the twoterm autoregression model of the predicted temperature was conducted by using GP. The two models were the mediumterm model based on the temperature inflexion and the shortterm model based on the temperature neighboring to BTP. The BTP was obtained by the cubic curve fitting of the predicted temperature. Simulation results proved the superiority of the twoterm prediction model.

出版日期: 2010-07-01
:  TP 181  
基金资助:

国家自然科学基金资助项目(60736021);国家“863”高技术研究发展计划资助项目(2006AA04Z184, 2007AA041406);浙江省科技计划资助项目(2006C11066,2006C31051);浙江省自然科学基金资助项目(Y4080339).

通讯作者: 卢建刚,男,教授.     E-mail: jglu@iipc.zju.edu.cn
作者简介: 商秀芹(1983—),女,山东聊城人,博士生,从事智能建模与优化算法的研究.Email: xqshang@iipc.zju.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  

引用本文:

商秀芹, 卢建刚, 孙优贤. 基于遗传规划的铁矿烧结终点2级预测模型[J]. J4, 2010, 44(7): 1266-1269.

SHANG Xiu-Qin, LEI Jian-Gang, SUN You-Xian. Genetic programming based twoterm prediction model of iron ore burning through point. J4, 2010, 44(7): 1266-1269.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2010.07.006        http://www.zjujournals.com/eng/CN/Y2010/V44/I7/1266

[1] VENKATARAMANA R, GUPTA S S, KAPUR P C. A combined model for granule size distribution and cold bed permeability in the wet stage of iron ore sintering process [J]. International Journal of Mineral Processing, 1999, 57(1): 4358.

[2] MENG J E, LIAO J, LIN J. Fuzzy neural networksbased quality prediction system for sintering process [J]. IEEE Transaction on Fuzzy System, 2000, 8(3): 314324.

[3] CHENG W S, FEI M R. A building of the geneticneural network for sinter’s burning through point [C]∥ Proceeding of 2004 International Conference on Information Acquisition. Hefei, China: IEEE, 2004: 479483.

[4] KOWN W H, KIME Y H, LEE S J. Eventbased model and control algorithm for burn through point in sintering processes [J]. IEEE Transactions on Control Systems Technology, 1999, 7(1): 3141.

[5] YONG H K, WOOK H K. An application of minmax generalized predictive control to sintering processes [J]. Control Engineering Practice, 1998, 6(8): 9991007.

[6] MIN J X, DUAN W P, CAO W H, et al. Coordinating fuzzy control of the sintering process [C]∥Proceedings of the 17th World Congress the International Federation of Automatic Control. Seoul, Korea: Elsevier, 2008: 77177722.

[7] ZHANG J H, XIE A G, SHEN F M. Multiobjective optimization and analysis model of sintering process based on BP neural network [J]. International Journal of Iron and Steel Research, , 2007, 14(2): 15.

[8] WU X F, FEI M R, WANG H S, et al. Prediction of sinter burnthrough point based on support vector machines [C]∥ The International Conference on Intelligent Computing. Kunming, China: Springer, 2006: 722730.

[9] BRADLEY P S, FAYYAD U M. Refining initial points for Kmeans clustering [C]∥Proceeding of the 15th International Conference on Machine Learning. Madison, USA: Morgan Kaufmann, 1998: 9199.

[10] CHENG W S. Prediction system of burning through point (BTP) based on adaptive pattern clustering and feature map [C]∥ Proceedings of 5th International Conference on Machine Learning and Cybernetics. Dalian, China: IEEE, 2006: 30893094.

[11] WU Y L, LU J G, XU J, et al. Bioprocess modeling using fuzzy regression clustering and genetic programming [C]∥Proceeding of the 6th World Congress on Intelligent Control and Automation. Dalian, China: [s.n.], 2006:93379341.

[12] 贺诗波,刘祥官,郜传厚,等.高炉硅含量预测控制的时间序列混合建模[J].浙江大学学报:工学版,2007, 41(10): 17391742.

HE Shibo, LIU Xiangguan, GAO Chuanhou, et al. Hybrid time series predictive control model for silicon content in blast furnace hot metal [J]. Journal of Zhejiang University: Engineering Science, 2007, 41(10): 17391742.

[1] 林亦宁, 韦巍, 戴渊明. 半监督Hough Forest跟踪算法[J]. J4, 2013, 47(6): 977-983.
[2] 李侃,黄文雄,黄忠华. 基于支持向量机的多传感器探测目标分类方法[J]. J4, 2013, 47(1): 15-22.
[3] 王洪波, 赵光宙, 齐冬莲, 卢达. 一类支持向量机的快速增量学习方法[J]. J4, 2012, 46(7): 1327-1332.
[4] 艾解清, 高济, 彭艳斌, 郑志军. 基于直推式支持向量机的协商决策模型[J]. J4, 2012, 46(6): 967-973.
[5] 潘俊, 孔繁胜, 王瑞琴. 局部敏感判别直推学习机[J]. J4, 2012, 46(6): 987-994.
[6] 金卓军, 钱徽, 朱淼良. 基于倾向性分析的轨迹评测技术[J]. J4, 2011, 45(10): 1732-1737.
[7] 顾弘, 赵光宙. 广义局部图像距离函数下的图像分类与识别[J]. J4, 2011, 45(4): 596-601.
[8] 罗建宏,陈德钊. 兼顾正确率和差异性的自适应集成算法及应用[J]. J4, 2011, 45(3): 557-562.
[9] 徐磊, 赵光宙, 顾弘. 成对耦合分类器的多球体预处理方法[J]. J4, 2010, 44(2): 237-242.