案例推理及迭代学习在层流冷却控制中的应用

片锦香; 柴天佑; 李界家

doi:10.3724/SP.J.1004.2012.02032

案例推理及迭代学习在层流冷却控制中的应用

doi: 10.3724/SP.J.1004.2012.02032

1.
沈阳建筑大学信息与控制工程学院沈阳 110168;
2.
中国科学院沈阳自动化研究所信息服务与智能控制研究室沈阳 110016;
3.
东北大学自动化研究中心沈阳 110189;
4.
流程工业综合自动化国家重点实验室沈阳 110189

详细信息

通讯作者:
片锦香

计量
- 文章访问数: 1430
- HTML全文浏览量: 47
- PDF下载量: 826
- 被引次数: 0
出版历程
- 收稿日期: 2011-09-28
- 修回日期: 2012-08-02
- 刊出日期: 2012-12-20

Application of Case-based Reasoning and Iterative Learning to Laminar Cooling Process Control

1.
School of Information and Control Engineering, Shenyang Jianzhu University, Shenyang 110168;
2.
Laboratory of Information Service and Intelligent Control, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016;
3.
Research Center of Automation, Northeastern University, Shenyang 110189;
4.
State Key Laboratory of Integrated Automation for Process Industry, Shenyang 110189

摘要

摘要: 现有的卷取温度预报补偿模型和带钢批次间补偿模型中,由于案例推理(Case-based reasoning, CBR)系统中检索特征权重系数采用人工凑试的方法,难以获得满意的补偿作用,且由于缺乏迭代学习的初始工况条件的匹配算法,难以进行准确匹配和有效迭代.因此,本文针对这两个问题, 提出了基于神经网络技术的案例推理系统检索特征权重系数自动学习算法及迭代学习技术初始工况匹配算法,改进了卷取温度预报补偿模型和带钢批次间补偿模型,并采用国内某大型钢厂的现场实际数据进行实验研究.实验结果表明,与原有方法相比,带钢卷取温度的控制偏差减小了1.63℃,卷取温度精度控制在±10℃以内的命中率提高了14.5%.
- 层流冷却 /
- 卷取温度 /
- 案例推理 /
- 迭代学习
Abstract: In some previous study, the strip coiling temperature prediction compensator and batch to batch compensator cannot obtain good compensating results due to the manually adjusted weight parameters for index feature of the case-based reasoning (CBR) system. And exact match and effective iteration cannot be done for the lack of initial operating condition matching algorithm. For this reason, a method based on neural network technology is proposed to learn the weights parameters of the index features of CBR system, with an initial operating condition matching algorithm that uses iterative learning technique to improve prediction compensator and the batch to batch compensator. The proposed hybrid intelligent control method is applied to a large domestic steel plant, and the results show that the strip coiling temperature control error decrease 1.63℃ and the hit rate increased 14.5% where the coiling temperature errors are controlled in the range of ±10℃.
- Laminar cooling /
- coiling temperature /
- case-based reasoning (CBR) /
- iterative learning

HTML全文

参考文献(1)

[1]

Peng L G, Liu E Y, Zhang D H, Liu X H, Xu F. Development and application of advanced coiling temperature control system in hot strip mill. Advanced Materials Research, 2012, 421: 140-146[2] Xing G S, Ding J L, Chai T Y, Afshar P, Wang H. Hybrid intelligent parameter estimation based on grey case-based reasoning for laminar cooling process. Engineering Applications of Artificial Intelligence, 2012, 25(2): 418-429[3] Han B, Zhang Z H, Liu X H, Wang G D. Element tracking strategies for hot strip laminar cooling control. Journal of Iron and Steel Research , 2005, 12(3): 18-21[4] Dong Z K, Wang X, Wang X B, Li S Y, Zheng Y H. Application of weighted multiple models adaptive controller in the plate cooling process. Acta Automatica Sinica, 2010, 36(8): 1144-1150[5] Kumar R K, Sinha S K, Lahiri A K. An online parallel controller for the runout table of hot strip mills. IEEE Transactions on Control Systems Technology, 2001, 9(6): 821-830[6] Zheng Y, Li S Y, Wang X B. An approach to model building for accelerated cooling process using instance-based learning. Expert Systems with Applications, 2010, 37(7): 5364-5371[7] Zheng Y, Li S Y, Wang X B. Distributed model predictive control for plant-wide hot-rolled strip laminar cooling process. Journal of Process Control, 2009, 19(9): 1427-1437[8] Chai Tian-You, Wang Xiao-Bo. Application of RBF neural networks in control system of the slab accelerating cooling process. Acta Automatica Sinica, 2000, 26(2): 219-225(柴天佑, 王笑波. RBF神经网络在加速冷却控制系统中的应用. 自动化学报, 2000, 26(2): 219-225)[9] Li H X, Guan S P. Hybrid intelligent control strategy. Supervising a DCS-controlled batch process. IEEE Control Systems Magazine, 2001, 21(3): 36-48[10] Xie H B, Jiang Z Y, Liu X H, Wang G D, Tieu A K, Yang M, Manabe K. Application of fuzzy control of laminar cooling for hot rolled strip. Journal of Materials Processing Technology, 2001, 187-188: 715-719[11] Pian Jin-Xiang, Chai Tian-You. Hybrid intelligent control method for laminar cooling process of hot rolled strip. Journal of Northeastern University (Natural Science), 2009, 30(11): 1534-1537(片锦香, 柴天佑. 热轧带钢层流冷却过程混合控制方法. 东北大学学报(自然科学版), 2009, 30(11): 1534-1537)[12] Pian Jin-Xiang, Chai Tian-You, Li Jie-Jia. Rule and data driven strip coiling temperature model in laminar cooling process. Acta Automatica Sinica, 2012, 38(11): 1861-1869(片锦香,柴天佑,李界家.规则与数据驱动的层流冷却过程带钢卷取温度模型.自动化学报, 2012, 38(11): 1861-1869)[13] Watson I. Case-based reasoning is a methodology not a technology. Knowledge-Based Systems, 1999, 12(5-6): 303-308[14] Pal S K, De P K, Basak J. Unsupervised feature evaluation: a neuro-fuzzy approach. IEEE Transactions on Neural Networks, 2000, 11(2): 366-376[15] You B, Kim M, Lee D, Lee J, Lee J S. Iterative learning control of molten steel level in a continuous casting process. Control Engineering Practice, 2011, 19(3): 234-242[16] Ahn H S, Bristow D. Special issue on ''iterative learning control''. Asian Journal of Control, 2011, 13(1): 1-2

施引文献

资源附件(0)

访问统计