密闭鼓风炉熔炼过程炉况智能监视及预报系统
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
密闭鼓风炉熔炼过程是一个极其复杂的生产过程,其优化控制模型及相应软件系统的研究开发工作起步较晚,使得现场操作缺乏科学的指导依据。为此进行鼓风炉熔炼过程炉况智能监视及预报系统的研究,开发具有自主版权的建模和优化软件,将现有的人工智能等领域的重要成果应用于鼓风炉熔炼过程,对优化密闭鼓风炉生产具有重要的意义。
     本文以韶关冶炼厂铅锌密闭鼓风炉熔炼过程为背景,介绍了密闭鼓风炉熔炼过程炉况智能监视及预报系统的研究和设计方法。首先在基于机理分析的基础上,分析熔炼过程中存在的问题,并且得到影响鼓风炉况的关键因素;然后提出解决方案,将炉况智能监视及预报系统分为透气性模块、烧结块软化点模块、料面分布模块等;然后分别讨论了几个模块模型的建立过程方法。包括基于BP神经网络的鼓风炉透气性预报模型、结合模糊分类方法的基于线性回归和神经网络的烧结块软化点预报智能集成模型、炉顶料面分布模型;最终讨论了系统的结构、功能,并进行了系统软硬件设计,使系统得到实现,这里重点突出了系统软件的设计思想和设计方法。系统软件采用vc编制,主要包括了通讯模块、主监视模块、透气性模块、烧结块软化点模块、料面分布模块等。系统通过现场调试运行,实现了炉况参数监视,透气性和烧结块软化点与软熔点预测,炉顶料面分布模拟等功能。现场运行情况证实系统具有一定的可靠性和实用性,能够满足现场要求的精度。
Imperial Smelting Furnace (ISF) smelting process is a quite complex process. The optimizing control model and software are not fully developed at present, which make it hard to give scientific direction to the fieidwork. The ISF conditions monitoring and predicting system is designed for this target, which is significant for the optimization of ISF production by applying artificial intelligence, besides a integrative software of optimizing and modeling possessing self-copyright is expected.
    In this thesis Intelligent Monitoring and Predicting System of ISF conditions in Shaoguan Smelt is designed. Firstly the key factors that influence the ISF conditions are gained based on the analysis of mechanism of ISF, then the solution to problems in ISF smelting process is proposed. Intelligent monitoring and predicting system of ISF conditions is divided into permeability module, agglomerate Softening-Point module and charge level module, which concerns some models, including permeability prediction model based on the theory of Back Propagation Neural Network, intelligent integrated prediction model of agglomerate softening-point based on the theories of Linear Regression and neural network, charge level model. At last the system is expatiated in its structure and function, which is implemented by software and hardware design, here the thought and the methods of system-design are emphasized. The system software, developed by VC, comprises communication module, main monitoring module, permeability module, agglomerate Softening-Point module and charge level module. Functions of parameters monitoring, agglomerate softening-point predicting and charge level simulating are realized in debugging and running, the precision and reliability have been proved.
引文
[1] 《铜铅锌冶炼参考设计资料》编写组,《铜铅锌冶炼参考设计资料》,冶金工业出版社,1979
    [2] 夏圈世等 大规模工业过程系统的优化控制策略,控制与决策,1987.1:52~57
    [3] 刘洪霖,宝宏 著 化工冶金过程人工智能优化,冶金工业出版社,1999:211~212
    [4] 金川镍闪速炉计算机在线控制专题组,金川镍闪速炉计算机在线控制技术研究报告,1995
    [5] 万维汉,万百五,杨金义 闪速炉的神经网络冰镍质量模型与稳态优化控制研究,自动化学报,1999.25(6):800~803
    [6] Wu Min, Nakano Micho, She Jin-Hua. A Distributed Expert Control System for a Hydrometaliurgical Zinc Process. Control Engineering Practice, 1998(6): 1435~1446
    [7] Wu Min, Nakano Micho, She Jin-Hua. A Model-based Expert Control System for the Leaching Process in Zinc Hydrometallurgy, Expert Systems with Applications, 1999.16(1): 135~143
    [8] Wu Mill, Nakano Micho, She Jin-Hua. An Expert Control Strategy Using Neural Networks for the Electrolytic Process in Zinc Hydrometallurgy Proc. the 1999 IEEE CCA, 1999.2:1044~1049
    [9] 王耀南,王辉,彭建春等 复杂工业过程的综合集成智能控制,信息与控制,1999,28(4):298~304
    [10] 史卓群 “ISP”工艺发展的主要特点,鼓风炉炼铅锌,1990年第3期
    [11] 韶冶教培处,韶冶工人岗位培训教程,韶关冶炼厂,1994
    [12] P.G.J.Lisboa 著 现代神经网络应用,电子工业出版社,1996
    [13] Roth,M.W. Neural networks for extraction of weak targets in high clutter environments.IEEE Trans. Syst.Man and Cybem.,SMC-19,5,1210-1217(1989).
    [14] 袁曾任 著 人工神经元网络及其应用,清华大学出版社,1999
    [15] 王其红等 基于BP神经网络的化工过程建模研究,江苏石油化工学院学报,2000.6,12(2):45~47
    [16] S. Cho, Y. Cho, S. Yoon, Reliable Roll Force Prediction in Cold Mill Using Multiple Neural Network.IEEE Trans. on Neural Networks. Vol.8, No.4:874~882
    [17] Y. Z. Lu, S.W. Marhaiard, "Development and Application of an Integrated Neural System for an HDCL",IEEE Trans. on Neural Networks. Vol.8, No.6, 1997:1328~1337
    [18] Wang Yalin, GuiWeihua, ChenXiaofang, etal. Neural network modeling for composition prediction of Pb-Zn sinter in imperial smelting process. Proceedings of the Annual Chinese Automation Conference in the UK. Derby, England, 1999(Sept): 21~24
    [19] 焦李成 著 神经网络系统理论,西安电子科技大学出版社,1996
    [20] Wolfram H.S.,H.W. Geffers,Adaptive control of dynamic systems by back propagation networks,Neural networks, 1993,6(4):517~524
    [21] Antlers K.,John A.,A simple weight decay can improve generalization,Advances in neural information processing systems, 1992:950~957
    [22] Jack S.N.J,Wan J.,Weight smoothing to improve network generalization, IEEE Transactions on neural networks, 1994,5(6): 752~763
    [23] David S.c.,Ramesh C.J.,A robust back propagation learning algorithm for function approximation, IEEE Transactiom on neural networks, 1994,5(3):467~479
    
    
    [24] Jeff A.J.,Mark W.W.,Improved generalization using robust cost functions, IEEE, 1992,911~918
    [25] Chen H.C.,Peter B.R.,She L.L.,et al,Expert prediction,symbolic learning, and neural networks,IEEE Expert,1994,5(6): 21-27
    [26] 史忠植 著 神经计算,电子工业出版社,1993,65~69
    [27] 傅世敏,刘子久,安云沛 编译 高炉过程气体动力学,冶金工业出版社,1990.7
    [28] ISIJ,1982 No10
    [29] 蔡军林,韶冶铅锌密闭鼓风炉技术改造,有色冶炼1998年第4期
    [30] 罗发龙,李衍达 著 神经网络信号处理,电子工业出版社,1993:30~31
    [31] 戚德虎,康继昌 BP 神经网络的设计,计算机工程与设计 1998,19(2):48~50
    [32] 王文成 BP 神经网络中自适应学习率的研究,计算机科学,1995,22(4):48~50
    [33] 戚德虎 基于神经网络并行推理机的研究与实现,西北工业大学,1996
    [34] 周复恭,黄运成 编著 应用线性回归分析,中国人民大学出版社,1989
    [35] S.Weisbeeg 著 应用线性回归,中国统计出版社,1998
    [36] 陈晓方,桂卫华,蔡自兴,吴敏 过程控制中的智能集成建模方法,系统仿真学报,2001.8,13(增):8~41
    [37] 毕学工 著 高炉过程数学模型及计算机控制,冶金工业出版社,1996
    [38] 杨天钧 徐金梧 著 高炉冶炼过程控制模型,科学出版社,1995
    [39] 刘云彩 著 高炉布料规律,冶金工业出版社,1984
    [40] 陈增强等 基于WindowsNT 环境的工业锅炉监控系统设计,计算机工程与应用,2000.8:163~165
    [41] 裴景玉 基于Windows95平台的实时控制技术,工业控制计算机2000年13(3):36~40
    [42] 希望图书创作室译,Visual C++6.0技术内幕,北京希望电子出版社,1995
    [43] 汤天浩 智能监控系统:新的理论、方法与进展,上海海运学院学报,2001.9,22(3):17~21
    [44] 周冶平 ADO数据存取技术,江南学院学报第14卷第3期,1999.9,52~56
    [45] 郑城荣,段来盛 著 Microsoft Access2.0开发指南[M],人民邮电出版社,1999
    [46] 张鹏 多线程技术在自动控制系统中的应用,电子与自动化,1999.6,20~23
    [47] 刘金琨,王树青,张建明 高炉实时控制专家系统存在的问题及其解决方法,浙江大学学报,2000.11,34(6):613~618
    [48] 刘金琨,龚报钧,王树青 高炉分布式智能控制系统的研究,浙江大学学报,2000.3,34(2):194~200

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700