基于改进支持向量机的高炉一氧化碳利用率预测方法

doi:10.11949/j.issn.0438-1157.20141482

化工学报 ›› 2015, Vol. 66 ›› Issue (1): 206-214.DOI: 10.11949/j.issn.0438-1157.20141482

基于改进支持向量机的高炉一氧化碳利用率预测方法

安剑奇¹, 陈易斐², 吴敏¹

1 中国地质大学(武汉)自动化学院, 湖北武汉 430074;
2 中南大学信息科学与工程学院, 湖南长沙 410083

收稿日期:2014-10-07 修回日期:2014-10-17 出版日期:2015-01-05 发布日期:2015-01-05
通讯作者: 吴敏
基金资助:
国家自然科学基金项目(61203017);国家自然科学基金重点项目(61333002);国家高技术研究发展计划项目(2012AA040307)。

A prediction method for carbon monoxide utilization ratio of blast furnace based on improved support vector regression

AN Jianqi¹, CHEN Yifei², WU Min¹

1 School of Automation, China University of Geosciences, Wuhan 430074, Hubei, China;
2 School of Information Science and Engineering, Central South University, Changsha 410083, Hunan, China

Received:2014-10-07 Revised:2014-10-17 Online:2015-01-05 Published:2015-01-05
Supported by:
supported by the National Natural Science Foundation of China (61203017), the National Natural Science Foundation of China (Key Program) (61333002) and the National High Technology Research and Development Program of China (2012AA040307).

摘要/Abstract

摘要：

高炉冶炼是一个具有非线性、大时滞、大噪声、分布参数等特征的高度复杂生产过程。针对目前高炉现场以焦比为能耗评价指标却无法提供实时指导的问题, 研究以一氧化碳利用率为能耗评价指标, 提出一种基于改进支持向量机的高炉一氧化碳利用率预测方法。首先分析高炉炼铁过程机理, 结合互信息法得出影响一氧化碳利用率的相关操作因素。然后鉴于生产数据含噪高的特点, 采用小波去噪方法去除数据噪声干扰, 并且利用灰色相对关联度分析方法对操作参数进行时序配准, 消除时滞影响, 建立高炉一氧化碳利用率预测模型。在建模过程中, 将自适应粒子群与支持向量机回归方法相结合, 以克服模型参数选择的随机性, 提高了模型预测精度。现场实际数据的预测结果表明所提出方法的有效性, 能够实时精确地预测高炉一氧化碳利用率, 为后续高炉的优化操作和节能减排提供了及时有效的决策支持。

关键词: 高炉, 一氧化碳, 建模, 支持向量机, 预测, 自适应粒子群

Abstract:

Blast furnace is a highly complex production process with the characteristics of nonlinearity, large delay, big noise, parameters distribution, and so on. According to the problem that coke ratio is used as energy consumption evaluation index but can't provide real-time guidance in the blast furnace field, carbon monoxide utilization ratio is studied as the energy consumption index and a prediction method for it based on improved support vector regression(SVR) is proposed. Firstly, relevant operation factors are selected by analyzing the mechanism of blast furnace combined with mutual information method. Next, wavelet transform is used to remove the noise including in the production data. Additionally, relative gray correlation analysis is applied for temporal registration to avoid the time delay of blast furnace operation, and then the prediction model of carbon monoxide utilization ratio is established. Support vector regression method and adaptive particle swarm optimization algorithm(APSO) are united to overcome the randomness of the selection of parameters and improve the accuracy of the prediction model. The simulation results demonstrate that APSO-SVR provides an effective way to predict the carbon monoxide utilization, which serves as a scientific decision support for the following optimization of blast furnace operation as well as energy saving and emission reduction.

Key words: blast furnace, carbon monoxide, model, support vector regression, prediction, adaptive particle swarm optimization

中图分类号:

TP273

安剑奇, 陈易斐, 吴敏. 基于改进支持向量机的高炉一氧化碳利用率预测方法[J]. 化工学报, 2015, 66(1): 206-214.

AN Jianqi, CHEN Yifei, WU Min. A prediction method for carbon monoxide utilization ratio of blast furnace based on improved support vector regression[J]. CIESC Journal, 2015, 66(1): 206-214.

参考文献 21

[1]	Pan Hao (潘昊), Yu Haibin (于海滨), Fan Mingzhe (苑明哲). Modeling and analysis of energy using efficiency of the blast furnace [J]. Manufacturing Automation (制造业自动化), 2011, 33 (23): 142-144
[2]	Liu Hui (刘慧), Li Peiran (李沛然), Bao Zhejing (包哲静). Intelligent predictive modeling of blast furnace system [J]. Journal of Central South University: Science and Technology (中南大学学报:自然科学版), 2012, 43 (5): 1787-1794
[3]	Fan Zhigang (范志刚), Qiu Guibao (邱贵宝), Jia Juanyu (贾娟鱼). Method to predict the coke rate based on BP neural network [J]. Journal of Chongqing University: Science and Technology (重庆大学学报:自然科学版), 2002, 25 (6): 85-91
[4]	Chen Tiejun (陈铁军), Chen Huafang (陈华方). Research on coke ratio and temperature control algorithm in puddling based on chain system [J]. Control and Instruments in Chemical Industry (化工自动化及仪表), 2010, 37 (4): 26-28
[5]	Chi Yanbin, Yang Shuangping, Dong Jie. Research on technology of blast furnace optimization of operation principle [J]. Advanced Materials Research, 2012, 516/517: 401-403
[6]	Zhou Chuandian (周传典). Blast Furnace Ironmaking Production of Technical Manual (高炉炼铁生产技术手册)[M]. Beijing: Metallurgical Industry Press, 2005: 174-177
[7]	Lahm A H. Calculation and Analysis of Modern Blast Furnace Process (现代高炉过程的计算分析)[M]. Wang Xiaoliu (王筱留), trans.Beijing: Metallurgical Industry Press, 1987: 266-289
[8]	Na Shuren (那树人). Ironmaking Calculation Analysis (炼铁计算辨析)[M]. Beijing: Metallurgical Industry Press, 2010:161-199
[9]	Xiang Zhongyong (项钟庸), Wang Xiaoliu (王筱留), Yin Han (银汉). More discussion on evaluation method for productive efficiency of ironmaking blast furnace [J]. Iron and Steel, 2013, 48 (3): 86-91
[10]	Wei Hangyu (魏航宇). Analysis and practice of utilization rate of No.5 BF gas//Practical New Technology and Equipment of Efficient Ironmaking and Raw Material [C]. Hangzhou, 2013: 87-90
[11]	Hu Zhenggang (胡正刚). Strategy for improvement in utilization rate of No.5 BF gas in WISCO and its practice [J]. Wisco Technology (武钢技术), 2012, 50 (2): 8-11
[12]	Gao Chuanhou, Jian Ling, Luo Shihua. Modeling of the thermal state change of blast furnace hearth with support vector machines [J]. IEEE Transactions on Industrial Electronics, 2012, 50 (4): 725-730
[13]	Gao Chuanhou, Jian Ling, Liu Xueyi, Chen Jiming, Sun Youxian. Data-driven modeling based on volterra series for multidimensional blast furnace system [J]. IEEE Transactions on Neural Networks, 2011, 22 (12): 2272-2283
[14]	Han Min (韩敏), Liu Xiaoxin (刘晓欣). An extreme learning machine algorithm based on mutual information variable selection [J]. Control and Decision (控制与决策), 2014, 29 (9): 1576-1580
[15]	Gao Chuanhou (郜传厚), Jian Ling (渐令), Chen Jiming (陈积明), Sun Youxian (孙优贤). Data-driven modeling and predictive algorithm for complex blast furnace ironmaking process [J]. Acta Automatica Sinic (自动化学报), 2009, 35 (6): 725-730
[16]	Zeng Jiusun (曾九孙), Liu Xiangguan (刘祥官), Luo Shihua (罗世华), et al. Application of principal component regression and partial least square in blast furnace iron-making [J]. Journal of Zhejiang University: Sciences Edition (浙江大学学报: 理学版), 2009, 36 (1): 33-36
[17]	Madadi Z, Anand G V, Premkummar A B. Signal detection in generalizaed Gaussian noise by nonlinear wavelet denoising [J]. IEEE Transactions on Circuits and Systems, 2013, 60 (11): 2973-2986
[18]	Shi Jie, Ding Zhaohao, Lee Wei-Jen. Hybrid forecasting model for very-short termwind power forecasting based on grey relational analysis and wind speed distribution features [J]. IEEE Transactions on Smart Grid, 2014, 5 (1): 521-526
[19]	Wang Zhanneng (王占能), Xu Zuhua (徐祖华), Zhao Jun (赵均), Shao Zhijiang (邵之江). Coal-fired power plant boiler combustion process modeling based on support vector machine and load data division [J]. CIESC Journal (化工学报), 2013, 64 (12): 4496-4502
[20]	Zhou You (周游), Zhao Chengye (赵成业), Liu Xinggao (刘兴高). An iteratively adaptive particle swarm optimization approach for solving chemical dynamic optimization problems [J]. CIESC Journal (化工学报), 2014, 65 (4): 1296-1302
[21]	Zhan Zhihui, Zhang Jun, Li Yun. Adaptive particle swarm optimization [J]. IEEE Transactions on Systems, Man, and Cybernetics-Part B: Cybernetics, 2009, 39 (6): 1362-1381

基于改进支持向量机的高炉一氧化碳利用率预测方法

A prediction method for carbon monoxide utilization ratio of blast furnace based on improved support vector regression

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 21

相关文章 15

编辑推荐

Metrics

本文评价

[1]	闫琳琦, 王振雷. 基于STA-BiLSTM-LightGBM组合模型的多步预测软测量建模[J]. 化工学报, 2023, 74(8): 3407-3418.
[2]	尹刚, 李伊惠, 何飞, 曹文琦, 王民, 颜非亚, 向禹, 卢剑, 罗斌, 卢润廷. 基于KPCA和SVM的铝电解槽漏槽事故预警方法[J]. 化工学报, 2023, 74(8): 3419-3428.
[3]	陈国泽, 卫东, 郭倩, 向志平. 负载跟踪状态下的铝空气电池堆最优功率点优化方法[J]. 化工学报, 2023, 74(8): 3533-3542.
[4]	郭雨莹, 敬加强, 黄婉妮, 张平, 孙杰, 朱宇, 冯君炫, 陆洪江. 稠油管道水润滑减阻及压降预测模型修正[J]. 化工学报, 2023, 74(7): 2898-2907.
[5]	于源, 陈薇薇, 付俊杰, 刘家祥, 焦志伟. 几何相似涡流空气分级机环形区流场变化规律研究及预测[J]. 化工学报, 2023, 74(6): 2363-2373.
[6]	邵伟明, 韩文学, 宋伟, 杨勇, 陈灿, 赵东亚. 基于分布式贝叶斯隐马尔可夫回归的动态软测量建模方法[J]. 化工学报, 2023, 74(6): 2495-2502.
[7]	李艳辉, 丁邵明, 白周央, 张一楠, 于智红, 邢利梅, 高鹏飞, 王永贞. 非常规服役超临界锅炉的微纳尺度腐蚀动力学模型建立及应用[J]. 化工学报, 2023, 74(6): 2436-2446.
[8]	张中秋, 李宏光, 石逸林. 基于人工预测调控策略的复杂化工过程多任务学习方法[J]. 化工学报, 2023, 74(3): 1195-1204.
[9]	吴心远, 刘奇磊, 曹博渊, 张磊, 都健. Group2vec：基于无监督机器学习的基团向量表示及其物性预测应用[J]. 化工学报, 2023, 74(3): 1187-1194.
[10]	史克年, 郑景元, 钱宇, 杨思宇. 基于马尔可夫链的蒸汽动力系统两阶段随机规划[J]. 化工学报, 2023, 74(2): 807-817.
[11]	陈家辉, 杨鑫泽, 陈顾中, 宋震, 漆志文. 以离子液体密度为例的分子性质预测模型建模方法探讨[J]. 化工学报, 2023, 74(2): 630-641.
[12]	杨静, 林振康, 汤君, 樊铖, 孙克宁. 电池系统的故障特征以及多故障的诊断与识别[J]. 化工学报, 2022, 73(8): 3394-3405.
[13]	刘振宇. 煤地下气化低效的化学反应工程根源：滞留层及通道中的传质与反应[J]. 化工学报, 2022, 73(8): 3299-3306.
[14]	周新杰, 王建林, 艾兴聪, 随恩光, 王汝童. 基于IDPC-RVM的多模态间歇过程质量变量在线预测[J]. 化工学报, 2022, 73(7): 3120-3130.
[15]	周乐, 沈程凯, 吴超, 侯北平, 宋执环. 深度融合特征提取网络及其在化工过程软测量中的应用[J]. 化工学报, 2022, 73(7): 3156-3165.