Application of Optimal Control Strategy to Converter Gas Recovery System
-
摘要: 分析了转炉煤气回收工艺特点以及影响回收效果的重要因素,阐述了实现回收过程运行优化控制的相关工艺参数指标, 提出了一种基于提高CO浓度的 优化控制方案,利用模糊径向基函数(Radical basis function, RBF)神经网络在线辨识出炉口压差与CO浓度之间的数学模型,根据辨识模型实时调整压差控制回路设定值,通过控制系统跟踪调整 后的设定值,在辨识的过程中改进了网络学习算法,使辨识网络对学习参数变化具有较好的鲁棒性,并易于收敛.在应用 此优化控制方法对煤气回收系 统进行仿真分析的基础上,投入现场应用,结果表明,此优化控制策略能明显提高煤气回收的质量和品质,达到了良好的实 际应用效果.Abstract: The characteristics of converter gas recovery process and the important factor in the effect of recycling are analyzed, run indicators of process parameters to achieve optimal control of the recycling process are described, and an optimal control strategy to increase CO concentration is raised. Fuzzy radical basis function (RBF) neural network is used to online identify the mathematical model between pressure of converter mouth and the CO concentration. The identified model is used to optimize pressure settings and control the pressure of converter mouth near the set value, thus significantly increasing the effect of CO concentration. Network learning algorithm is improved in the process of identification, so that the network is robust and easy to convergence for the variational learning parameters. The application of the optimal control strategy in a gas recovery system shows that this optimal control strategy can significantly improve the quality and quality of gas recovery, and achieve good application results.
-
[1] Yan Ai-Jun, Chai Tian-You, Wang Pu. Intelligently optimizing control of magnetic-tube-recovery-rate (MTRR) based on variable prediction. Control Theory Applications, 2008, 25(5): 908-912 (严爱军, 柴天佑, 王普. 基于参量预报的磁选管回收率智能优化控制. 控制理论与应用, 2008, 25(5): 908-912)[2] Zhang Xing. Study and Design on Smoke Decontaminating and Coal Gas Reclaiming of Steel Making Engineering for 50t Converter at DeSheng I S(group) Corp [Master dissertation], Chongqing University, China, 2004(张醒. 德钢50t转炉炼钢工程烟气净化及煤气回收监控系统的研究与设计 [硕士学位论文], 重庆大学, 中国, 2004)[3] Chai Tian-You, Ding Jin-Liang, Wang Hong, Su Chun-Yi. Hybrid intelligent optimal control method for operation of complex industrial processes. Acta Automatica Sinica, 2008, 34(5): 505-515 (柴天佑, 丁进良, 王宏, 苏春翌. 复杂工业过程运行的混合智能优化控制方法. 自动化学报, 2008, 34(5): 505-515)[4] Wu Le, Yang Guo-Hua. New purification and recovery system for steel making converter flue gas. Energy for Metallurgical Industry, 2009, 28(5): 47-50 (武乐, 杨国华. 新型炼钢转炉煤气净化回收系统. 冶金能源, 2009, 28(5): 47-50)[5] Wang Ai-Hua, Cai Jiu-Ju, Li Xiu-Ping, Wang Ding, Zhou Qing-An. Converter gas recovery analysis and improvement. Iron and Steel, 2006, 41(5): 81-84(王爱华, 蔡九菊, 郦秀萍, 王鼎, 周庆安. 转炉煤气回收分析及其提高措施. 钢铁, 2006, 41(5): 81-84)[6] Song Hai-Ying, Gui Wei-Hua, Yang Chun-Hua, Wang Ya-Lin. Dynamic optimization control for the slag forming process in a Pierce-Smith converter. Control Theory Applications, 2009, 26(10): 1093-1099(宋海鹰, 桂卫华, 阳春华, 王雅琳. PS转炉造渣过程的动态优化控制. 控制理论与应用, 2009, 26(10): 1093-1099)[7] Cheng Li-Liang. Steel-making Converter Flue Gas Recycling Technology. Beijing: Metallurgical Industry Press, 1991. 85-86(成立良. 炼钢转炉烟气的回收利用技术. 北京: 冶金工业出版社, 1991. 85-86)[8] Du Yi-Wen. Design and Realization for Fume Cleaning and Recovery System of Converter [Master dissertation], Northeastern University, China, 2005 (杜一文. 转炉烟气净化回收系统的设计与实现 [硕士学位论文], 东北大学, 中国, 2005)[9] Chen Zhi-Bin. The current state and development of recovery and utilization technology of domestic converter gas. Metallurgical Power, 2003, (1): 9-12(陈志斌. 国内转炉煤气回收利用技术的现状及发展. 冶金动力, 2003, (1): 9-12)[10] Liu Yin-Mian. Application of the micro-differential pressure technology in converter gas recovery. Steel, 1994, 29(5): 60-62 (刘荫绵. 炉口微差压技术在转炉煤气回收中的应用. 钢铁, 1994, 29(5): 60-62)[11] Deng Y, He X N, Zhao J, Xiong Y, Shen Y Q, Jiang J. Application of artificial neural network for switching loss modeling in power IGBTs. Journal of Zhejiang University-Science C, 2010, 11(6): 435-443[12] Chen Xiao-Qu, Lu Cong-Da, Liao Zhi-Ping. Improvement of BP learning algorithm in Matlab. Control Engineering of China, 2005, 12(S): 96-98(陈孝趋, 鲁聪达, 廖枝平. BP算法的改进及其在Matlab上的实现. 控制工程, 2005, 12(S): 96-98)[13] Shenoi B A. Introduction to Digital Signal Processing and Filter Design. USA: John Wiley Sons, 2006. 112-115[14] Guo Peng, Hu Hui, Liu Guo-Rong, Liu Dong-Bo. Adaptive neural-network tracking control for SISO affine nonlinear systems with zero-dynamics. Control Theory Applications, 2010, 27(8): 1113-1117(郭鹏, 胡慧, 刘国荣, 刘洞波. 具有零动态的SISO仿射非线性系统的神经网络自适应跟踪控制. 控制理论与应用, 2010, 27(8): 1113-1117)[15] Qiao Jun-Fei, Han Hong-Gui. Optimal structure design for RBFNN structure. Acta Automatica Sinica, 2010, 36(6): 865-872(乔俊飞, 韩红桂. RBF神经网络的结构动态优化设计. 自动化学报, 2010, 36(6): 865-872)[16] Venkatesan P, Anitha S. Application of a radial basis function neural network for diagnosis of diabetes mellitus. Research Articles, 2006, 91(9): 1195-1199[17] Bao Hong, Huang Xin-Han, Li Xi-Xiong. Generalized fuzzy inference and generalized fuzzy RBF networks. Control and Decision, 2000, 15(2): 205-208(鲍鸿, 黄心汉, 李锡雄. 广义模糊推理与广义模糊RBF神经网络. 控制与决策, 2000, 15(2): 205-208)[18] Wu Yun-Jie, Liu Jin-Kun, Liu Qiang. Servo table robust control based on fuzzy RBF neural network. Journal of System Simulation, 2002, 14(9): 1222-1234(吴云洁, 刘金琨, 刘强. 基于模糊RBF网络的伺服转台鲁棒控制. 系统仿真学报, 2002, 14(9): 1222-1234)[19] Liu Jin-Kun. Advanced PID Control and MATLAB Simulation. Beijing: Publishing House of Electronics Industry, 2006. 79-80, 288-299 (刘金琨. 先进PID控制MATLAB仿真. 北京: 电子工业出版社, 2006. 79-80, 288-299)
点击查看大图
计量
- 文章访问数: 1813
- HTML全文浏览量: 66
- PDF下载量: 765
- 被引次数: 0