基于动态神经网络的高炉炉壁不完备温度检测信息软测量方法
|
摘要
针对高炉炉壁温度检测系统中由于传感器故障导致的检测信息不完备问题,提出一种基于动态神经网络的不完备检测信息软测量方法。首先,依据高炉结构和炉壁温度传感器位置分布建立温度传感器位置描述模型和分区域温度检测模型;其次,根据热传递学分析炉壁分区域温度检测模型中各个传感器之间存在的相关性,并采用最大互信息非参统计量方法从传感器检测序列上定量的计算分区域温度检测模型中各传感器间的相关度;最后,依据相关性分析结果,结合温度传递规律,提出炉壁不完备温度检测信息软测量模型,采用Elman神经网络对模型的结构和参数进行辨识。通过高炉冶炼现场采集的数据仿真计算表明,提出的方法具有较好的准确度与检测精度,能够满足现场的检测精度要求,具备广泛的应用价值。
For the missing information problem caused by faulted temperature sensor in temperature detecting system on blast furnace(BF) wall, a soft-sensing method based on dynamic neural network is proposed. Firstly, the temperature sensor position model and regional temperature measurement model are built based on the structure of BF. Then, according to heat transfer mechanism, the correlation between temperature sensors in regional temperature measurement model is quantitatively calculated by using maximal information coefficient(MIC) method. Finally, the soft-sensing model for missing temperature information is proposed by using Elman neural network to identify the structure of the model. The effectiveness and feasibility of the proposed method is proved by the simulation results of the real-time producing data of blast furnace which satisfies the field detection accuracy requirement.
For the missing information problem caused by faulted temperature sensor in temperature detecting system on blast furnace(BF) wall, a soft-sensing method based on dynamic neural network is proposed. Firstly, the temperature sensor position model and regional temperature measurement model are built based on the structure of BF. Then, according to heat transfer mechanism, the correlation between temperature sensors in regional temperature measurement model is quantitatively calculated by using maximal information coefficient(MIC) method. Finally, the soft-sensing model for missing temperature information is proposed by using Elman neural network to identify the structure of the model. The effectiveness and feasibility of the proposed method is proved by the simulation results of the real-time producing data of blast furnace which satisfies the field detection accuracy requirement.
引文
[1]周传典.高炉炼铁生产技术手册[M].北京:冶金工业出版社,2002.ZHOU C D.The Technical Manual of Blast Furnace Ironmaking[M].Beijing:Metallurgical Industry Press,2002.
[2]PEACEY J G,DAVENPORT W G.The Iron Blast Furnace:Theory and Practice[M].Holland:Elsevier,2013.
[3]李洋龙,程树森.铜冷却壁冷却恢复技术的传热过程[J].钢铁研究学报,2012,24(7):5-9.LI Y L,CHENG S S.Cooling capacity recovery of copper stave based on heat transfer[J].Journal of Iron and Steel Research,2012,24(7):5-9.
[4]代兵,张建良,姜喆,等.高炉铸铜冷却壁热面状况计算模型的开发与实践[J].冶金自动化,2012,36(5):37-41.DAI B,ZHANG J L,JIANG Z,et al.Development and practice of cast copper cooling stave hot surface status calculation model of blast furnace[J].Metallurgical Industry Automation,2012,36(5):37-41.
[5]赵宏博,程树森,霍守锋.高炉炉缸炉底温度场及异常侵蚀在线监测诊断系统[J].钢铁,2010,(5):11-16.ZHAO H B,CHENG S S,HUO S F.On-line monitoring system for temperature field and abnormal erosion of bf hearth and bottom[J].Iron and Steel,2010,(5):11-16.
[6]吴俐俊,孙国平,陆祖安.热面局部高温下高炉冷却壁智能监测试验研究[J].钢铁,2011,46(5):11-14.WU L J,SUN G P,LU Z A.Experiment study on intelligent prediction of blast furnace stave on the surface with local high temperature[J].Iron and Steel,2011,46(5):11-14.
[7]AN J Q,WU M,HE Y.A temperature field detection system for blast furnace based on multi-source information fusion[J].Intelligent Automation&Soft Computing,2013,19(4):625-634.
[8]安剑奇,吴敏,何勇,等.基于多源信息可信度的高炉料面温度检测方法[J].上海交通大学学报,2012,46(12):1945-1950.AN J Q,WU M,HE Y,et al.Temperature detection method of blast furnace surface based on the reliability of multi-source information[J].Journal of Shanghai Jiaotong University,2012,46(12):1945-1950.
[9]SAXEN H,GAO C,GAO Z.Data-driven time discrete models for dynamic prediction of the hot metal silicon content in the blast furnace—a review[J].Industrial Informatics,IEEE Transactions on,2013,9(4):2213-2225.
[10]张向宇,郑树,周怀春,等.基于热辐射成像建模求解的管式炉炉管温度检测[J].化工学报,2015,66(3):965-971.DOI:10.11949/j.issn.0438-1157.20141478.ZHANG X Y,ZHENG S,ZHOU H C,et al.Visualization of pipe temperature distribution in tubular furnace based on radiation imaging model solving[J].CIESC Journal,2015,66(3):965-971.DOI:10.11949/j.issn.0438-1157.20141478.
[11]WU M,LEI Q,CAO W,et al.Integrated soft sensing of coke-oven temperature[J].Control Engineering Practice,2011,19(10):1116-1125.
[12]TIAN H X,MAO Z Z.An ensemble elm based on modified Ada Boost.RT algorithm for predicting the temperature of molten steel in ladle furnace[J].Automation Science and Engineering,IEEE Transactions on,2010,7(1):73-80.
[13]鄂加强,王耀南,梅炽.铜精炼过程铜液温度软测量模型及应用[J].化工学报,2006,57(1):203-209.E J Q,WANG Y N,MEI C.Soft-sensing model of copper liquid temperature in copper refining process and its application[J].Journal of Chemical Industry and Engineering(China),2006,57(1):203-209.
[14]KHALEGHI B,KHAMIS A,KARRAY F O,et al.Multisensor data fusion:a review of the state-of-the-art[J].Information Fusion,2013,14(1):28-44.
[15]AZIZ A M.A new multiple decisions fusion rule for targets detection in multiple sensors distributed detection systems with data fusion[J].Information Fusion,2014,18:175-186.
[16]NIU G,YANG B S,PECHT M.Development of an optimized condition-based maintenance system by data fusion and reliabilitycentered maintenance[J].Reliability Engineering&System Safety,2010,95(7):786-796.
[17]侯彦东,陈志国,汤天浩.多传感器故障检测与隔离算法[J].化工学报,2010,61(8):2008-2014.HOU Y D,CHEN Z G,TANG T H.Multi-sensor fault detection and isolation algorithm[J].CIESC Journal,2010,61(8):2008-2014.
[18]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.DOI:10.11949/j.issn.0438-1157.20141482.AN J Q,CHEN Y F,WU M.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.DOI:10.11949/j.issn.0438-1157.20141482.
[19]RESHEF D N,RESHEF Y A,FINUCANE H K,et al.Detecting novel associations in large data sets[J].Science,2011,334(6062):1518-1524.
[2]PEACEY J G,DAVENPORT W G.The Iron Blast Furnace:Theory and Practice[M].Holland:Elsevier,2013.
[3]李洋龙,程树森.铜冷却壁冷却恢复技术的传热过程[J].钢铁研究学报,2012,24(7):5-9.LI Y L,CHENG S S.Cooling capacity recovery of copper stave based on heat transfer[J].Journal of Iron and Steel Research,2012,24(7):5-9.
[4]代兵,张建良,姜喆,等.高炉铸铜冷却壁热面状况计算模型的开发与实践[J].冶金自动化,2012,36(5):37-41.DAI B,ZHANG J L,JIANG Z,et al.Development and practice of cast copper cooling stave hot surface status calculation model of blast furnace[J].Metallurgical Industry Automation,2012,36(5):37-41.
[5]赵宏博,程树森,霍守锋.高炉炉缸炉底温度场及异常侵蚀在线监测诊断系统[J].钢铁,2010,(5):11-16.ZHAO H B,CHENG S S,HUO S F.On-line monitoring system for temperature field and abnormal erosion of bf hearth and bottom[J].Iron and Steel,2010,(5):11-16.
[6]吴俐俊,孙国平,陆祖安.热面局部高温下高炉冷却壁智能监测试验研究[J].钢铁,2011,46(5):11-14.WU L J,SUN G P,LU Z A.Experiment study on intelligent prediction of blast furnace stave on the surface with local high temperature[J].Iron and Steel,2011,46(5):11-14.
[7]AN J Q,WU M,HE Y.A temperature field detection system for blast furnace based on multi-source information fusion[J].Intelligent Automation&Soft Computing,2013,19(4):625-634.
[8]安剑奇,吴敏,何勇,等.基于多源信息可信度的高炉料面温度检测方法[J].上海交通大学学报,2012,46(12):1945-1950.AN J Q,WU M,HE Y,et al.Temperature detection method of blast furnace surface based on the reliability of multi-source information[J].Journal of Shanghai Jiaotong University,2012,46(12):1945-1950.
[9]SAXEN H,GAO C,GAO Z.Data-driven time discrete models for dynamic prediction of the hot metal silicon content in the blast furnace—a review[J].Industrial Informatics,IEEE Transactions on,2013,9(4):2213-2225.
[10]张向宇,郑树,周怀春,等.基于热辐射成像建模求解的管式炉炉管温度检测[J].化工学报,2015,66(3):965-971.DOI:10.11949/j.issn.0438-1157.20141478.ZHANG X Y,ZHENG S,ZHOU H C,et al.Visualization of pipe temperature distribution in tubular furnace based on radiation imaging model solving[J].CIESC Journal,2015,66(3):965-971.DOI:10.11949/j.issn.0438-1157.20141478.
[11]WU M,LEI Q,CAO W,et al.Integrated soft sensing of coke-oven temperature[J].Control Engineering Practice,2011,19(10):1116-1125.
[12]TIAN H X,MAO Z Z.An ensemble elm based on modified Ada Boost.RT algorithm for predicting the temperature of molten steel in ladle furnace[J].Automation Science and Engineering,IEEE Transactions on,2010,7(1):73-80.
[13]鄂加强,王耀南,梅炽.铜精炼过程铜液温度软测量模型及应用[J].化工学报,2006,57(1):203-209.E J Q,WANG Y N,MEI C.Soft-sensing model of copper liquid temperature in copper refining process and its application[J].Journal of Chemical Industry and Engineering(China),2006,57(1):203-209.
[14]KHALEGHI B,KHAMIS A,KARRAY F O,et al.Multisensor data fusion:a review of the state-of-the-art[J].Information Fusion,2013,14(1):28-44.
[15]AZIZ A M.A new multiple decisions fusion rule for targets detection in multiple sensors distributed detection systems with data fusion[J].Information Fusion,2014,18:175-186.
[16]NIU G,YANG B S,PECHT M.Development of an optimized condition-based maintenance system by data fusion and reliabilitycentered maintenance[J].Reliability Engineering&System Safety,2010,95(7):786-796.
[17]侯彦东,陈志国,汤天浩.多传感器故障检测与隔离算法[J].化工学报,2010,61(8):2008-2014.HOU Y D,CHEN Z G,TANG T H.Multi-sensor fault detection and isolation algorithm[J].CIESC Journal,2010,61(8):2008-2014.
[18]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.DOI:10.11949/j.issn.0438-1157.20141482.AN J Q,CHEN Y F,WU M.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.DOI:10.11949/j.issn.0438-1157.20141482.
[19]RESHEF D N,RESHEF Y A,FINUCANE H K,et al.Detecting novel associations in large data sets[J].Science,2011,334(6062):1518-1524.