高炉炉顶煤气温度分布模式识别神经元网络的研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
煤气流的分布关系到炉内温度分布、软熔带结构、炉况顺行和煤气的利用状况,最终影响到高炉冶炼指标。高炉操作也主要是围绕获得合理、适宜的煤气流分布来进行的,另一方面,煤气流分布也是高炉操作者判断炉况的重要依据。
     由于高炉是个封闭式系统,炉内煤气流的变化是不可见的,只有通过传感器数据对炉况进行判断。传统的判断方法是基于纯机理性的数学模型来研究高炉内煤气流分布,但这种方法通常过于复杂,受在线实时的制约,难以进行实时在线分析和控制,因此不能及时反馈信息,调整布料制度。人工神经网络模型具有很强的容错性、学习性、自适应性和非线性的映射能力,特别适合于解决因果关系复杂的非确定性推理、判断、识别和分类等问题,它由网络拓扑结构、神经元特性函数和学习方法确定。高炉生产过程是大型的分布参数系统,可用大量传感器得到其高度和半径方向上的各种检测值,然后用人工神经网络来识别它们的特征分布模式,进行炉况诊断和控制。
     鉴于实际中煤气流分布并没有固定的分布模式,本文应用了一种自组织神经网络来进行煤气流模式识别。自组织神经网络是一类无导师学习网络,它可以自动地向环境学习,可以对任意多和任意复杂的二维模式进行自组织、自稳定和大规模并行处理,在无监督的情况下从输入数据中找出有意义的规律来。我们应用这种网络方法从我国宝钢1号高炉大量十字测温历史数据中自动整理出5×5=25种分布模式来,这25种分布模式将映射在一个二维网络图上,并且相近的模式在图上的坐标位置也是靠近的,即该方法有归类的作用。借助于该模型,高炉操作者将可更直接更方便地判断煤气流的分布情况,从而更好地指导高炉操作。该模型方便地表达和描述了实际气流分布状况,并方便了建立十字测温数据与布料模式及料面形状、矿焦比等之间的关系。该模型是宝钢1号高炉总布料推定模型的一个子模型,已在线运行。
Gas flow distribution is correlative with the temperature distribution in blast furnace, the shape of the cohesive zone, the smooth state of blast furnace and using status of gas flow , finally influence the smelting index of blast furnace. The target of blast furnace operation mainly is to achieve proper and optimum gas flow distribution. At the same time, the gas flow distribution also is the important foundation for blast furnace operators to estimate the state of blast furnace.
    The blast furnace is a closed system, and the change of gas flow distribution is invisible, so the only method of estimate the status of blast furnace is to utilize records of all kinds of sensors. The conventional ways of identifying gas flow distribution is mathematic model based absolute mechanism. But this method is too complex , be subjected to on line operation and is difficult to on line analyzing and control , so can not to feedback information in time and to adjust burden rule. The artificial neural network model has strong fault - tolerant performance, learning performance, self-adaptive performance and non - linearity map ability, and it is adaptive to solve some problems like non - determinacy inference of complex causal relation , judgment , recognition , classification and so on. The artificial neural network model is defined by network topological structure, neuron characteristic function and learning method. The production process of blast furnace is a large - scale distribution parameter sys
    tem. We can obtain all kinds of detection value in altitude - direction and radius - direction by many sensors. After that, to recognize their character distribution patterns by artificial neural network, and using these to diagnose and control the condition of blast furnace.
    
    
    In fact, gas flow has not immovable distribution patterns, so this paper recognize gas flow distribution pattern by a self-organization neural network. The self organization neural network is a kind of unsupervised learning network, it can learns automatically from surrounding, can self -organize, self - stabilize and large-scale parallel - process random multi and complex two - dimensional patterns, and find some significative rules from inputted data in the condition of unsupervised data. We arranged 25 gas flow distribution patterns (5X5) from multiple production data of the Ne 1 blast furnace of Bao Steel, the 25 patterns are mapped on a two - dimensional net diagram , but also the coordinates of those similar patterns is also closer in the diagram, namely, the method has classified function. Using this model, the operators can recognize expediently gas flow'distribution. The model describes expediently actual gas flow distribution, and establishes expediently the relation between temperature data, burde
    n mode, charge shape, the ore - to - coke ratio, and so on. The model is a sub - model of distribution model of Ne 1 blast furnace of Bao Steel, and is working on line.
引文
[1] 高谷幸司,最近高炉,铁钢,1995,8(11),pp 1031-1036。
    [2] 严定鎏、齐渊洪、许梅川、赫冀成,高炉软熔带气体流动的数值模拟,钢铁研究学报,1999,11(1),pp 5。
    [3] 王永庆,人工智能原理与方法,西安交通大学出版社,1998。
    [4] 王玉涛、姜会研等,混合神经网络及其在高炉径向煤气流模式分布中的应用,沈阳工业大学学报,1999年6月第3期,pp 265-268。
    [5] 钟勇,高炉炉喉煤气流分布数学模型,钢铁钒钛,1998年8月第3期,pp 59-64。
    [6] Yoshihisa OTSUKA, Masami KONISHI, Kunihiro HANOKA and Takcshi MAKI, Forecasting Heat Level in Blast Furnace Using a Neural Network Model, ISIJ international, Vol.39(1999).NO. 10 pp 1047-1052.
    [7] Leif Lassus and Henrik Saxen, Operation Diagrams Based on Blast Furnace Wall Temperatures, IRONMAKING CONFERENCE PROCEEDINGS, 1999, pp. 75-79.
    [8] 大冢喜久,/制御/情报,1999,35(4) pp 74-80。
    [9] 艾立群,人工神经网络在钢铁工业中的应用,钢铁研究学报,1997年8月第4期,pp 60-63。
    [10] 平田达郎等,高炉认识适用,计装,1990,33(3):pp 27-31。
    [11] 杨自厚、许宝栋,神经网络在高炉模式识别中的应用,冶金自动化,1992年9月第5期,pp3-6。
    [12] 杨尚宝、刘文全,人工智能在高炉控制中的应用,炼铁,1994年第5期,pp 43-47。
    [13] 李士勇,模糊控制·神经控制和智能控制论,哈尔滨工业大学出版社,1998.9。
    [14] 张际先、宓霞,神经网络及其在工程中的应用,机械工业出版社,1996。
    [15] 顾家成、徐守厚、吕同冈,宝钢1号高炉的操作实践,钢铁,1994年5月第5期,pp5-12。
    [16] 王莜留,钢铁冶金学(炼铁部分),冶金工业出版社,1991。
    [17] 刘云彩,装料制度,炼铁,1989年第6期,pp 47-53。
    [18] 刘云彩,高炉布料规律,冶金工业出版社,1984。
    [19] 傅世敏、刘子久、安云沛,高炉过程气体动力学,冶金工业出版社。
    
    
    [20] 李国成,高炉炉况失常的处理及预防,南方钢铁,1989年第4期,pp 4-7。
    [21] 邓守强,高炉炼铁新技术,冶金工业出版社,1990。
    [22] 岩村忠昭,川崎制铁技报,Vol.13,1981,No.1,pp 129。
    [23] 安云沛,1982年辽宁省金属学会烧结炼铁论文集,1982,pp 21。
    [24] 大槻满,日本鋼管技报,No.68,1975,pp 23。
    [25] 胡伯康,宝钢1号高炉低焦比操作经验,炼铁,1992年第4期,pp 34-36。
    [26] C. Thirion, R. Capelani, D. Flamion and R. Nicolle, FRENCH BLAST FURNACE OPERATION CONTROL BY USING INSTRUMENTATION AND MATHEMATICAL MODELS, European Ironmaking Congress, 14-17 September, 1986, Aachen.
    [27] 木村亮介、宫原弘明等,事例高炉装入物分布制御学习,NKK技报,No.142(1993),pp 46-51。
    [28] Friedrich Bordemann、Walter H. Hartig、Hans-Jochen Grisse, INTEGRATED USE OF BURDEN PROFILE PROBE AND IN-BURDEN PROBE FOR GAS FLOW CONTROL IN THE BALST FURNACE, IRONMAKING CONFERENCE PROCEEDINGS, 1995, pp 259.
    [29] S. K. Jung、Y. J. Lee、Y. K. Suh、T. J. Ahn and S. M. Kim, BURDEN DISTRIBUTION CONTROL FOR MAINTAINING THE CENTRAL GAS FLOW AT NO. 1 BLAST FURNACE IN POHANG WORKS, IRONMAKING CONFERENCE PROCEEDINGS, 1995, pp 241.
    [30] 杨天钧、徐金梧,高炉冶炼过程控制模型.北京,科学出版社,1995。
    [31] H. Nishiho and T. Ariyama, Influence of Gas Flow on Burden Distribution in Blast Furnace, Tetsu-to-Hagane, 66, 1980, pp 1878-1887.
    [32] K. Takeda、Y. Konishi and T. Fukutake, Burden Distribution in Case of Low Gas Temperature at the Center of Upper Shaft, Tetsu-to - Hagane, 73, 1987, pp 2084-2091.
    [33] 朱仁良,高炉炉腰温度低时的煤气流分布调节,钢铁,1991年7月第7期,pp 1-5。
    [34] 刘志远,高炉低料线的处理,鞍钢技术,2002年第3期,pp 20-22。
    [35] 陈革,炉身上部径向煤气流及其对高炉操作的影响,冶金译丛,1998年第1期,pp 13-21。
    [36] Koichi Orsuka、Yoshiyuki Matoba et al, A HYBRID EXPERT SYSTEM COMBIND WITH A MATHEMTICAL MODEL FOR BLAST FURNACE OPERATION, Proceedings of the Sixth International Iron and Steel Congress, 1990, Nagory ISIJ.
    [37] Yoshio Okuno、Kazuya Kunimoto et al, DEVELOPMENT OF A MATHEMATICAL MODEL FOR
    
    BURDEN DISTRIBUTION IN A BLAST FURNACE, Ironmaking Conference Proceeding, 1988, pp 543-552.
    [38] G.S. Antoine et al, Blast Furnace Burden and Gas Distribution, Real Size Model Experiments, The International Congress of Science and Technology of Ironmnking, 1994, pp 198-204.
    [39] 田广军、吴淑华,1号高炉后期布料模式,宝钢技术,1995年第5期.pp 30-32。
    [40] 邓炳炀、胡伯康,宝钢1号高炉生产技术的进步,炼铁,1992年第1期,pp 30-32。
    [41] 李维国,宝钢1号高炉的操作实践,钢铁,1989年9月第9期,pp4-12。
    [42] 徐勇、荆涛等译,神经网络模式识别及其实现,电子工业出版社,pp 165-200。
    [43] 黄德双,神经网络模式识别系统理论.北京,电子工业出版社,1996。
    [44] 毕学工,高炉过程数学模型及计算机控制,冶金工业出版社,1996。
    [45] 熊玮,无钟高炉布料数学模型,武汉科技大学硕士学位论文,2000。

© 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