转炉炼钢中的炉口火焰线性回归分析
|
摘要
提出了将转炉炉口火焰光强及图像信息相结合,用于转炉炼钢的终点判断的新方法。构建了相应的实验研究系统。该系统主要包括炉口火焰光强信息采集、炉口火焰图像信息采集、炉口火焰光强及图像数据分析、处理软件等几部分。利用望远系统以及数字摄像系统构建了炉口火焰图像采集系统,利用光纤谱分复用和DirectShow技术设计了炉口辐射多频道信息获取系统,选择了特定的火焰图像数据处理方法。对所涉及的硬件(炉口火焰图像采集、光学系统设计、数据提取),软件(炉口火焰图像特征值分析)系统进行调试后用于现场试验。通过对实验数据分析并发现,光强与图像特征信息在炼钢吹炼过程中存在着初期逐步变大、中期剧烈振荡,临近终点时两者出现了相反的变化趋势。在此基础上,运用多元回归方法建立起不同炉次终点时刻的数学模型。模型的显著性检验结果为:样本决定系数为0.98,F检验值为416.19远大于临界值2.36,表明模型显著且拟合程度好。模型的实验预测精度为91.7%,适合转炉在线终点控制和快速出钢模型的要求。
To judge steelmaking end-point of the converter online, a new method based on the unifying of the flame radiation intensity and the image information from converter mouth is presented in this dissertation. And the corresponding experimental system has been constructed. This system is mainly consist of a multi-frequency information acquisition system,which was designed based on multi-single spectrum by use of optical fiber and DirectShow. The experiment results show that the light intensity and the image characteristic information have the remarkable varying tendency in the steelmaking blowing process. Based on this phenomenon, mathematical model of the end-point time had been established by use of the regression analysis method. The significance test results show that the sample determination coefficient is 0.98 and the F-test value is 416.19 bigger than the critical value 2.36. Therefore the model has good fitting degree and the regression equation is significant. The prediction precision of the model is 91.7%, and it suits the converter end-point control online and the fast tapping model request.
To judge steelmaking end-point of the converter online, a new method based on the unifying of the flame radiation intensity and the image information from converter mouth is presented in this dissertation. And the corresponding experimental system has been constructed. This system is mainly consist of a multi-frequency information acquisition system,which was designed based on multi-single spectrum by use of optical fiber and DirectShow. The experiment results show that the light intensity and the image characteristic information have the remarkable varying tendency in the steelmaking blowing process. Based on this phenomenon, mathematical model of the end-point time had been established by use of the regression analysis method. The significance test results show that the sample determination coefficient is 0.98 and the F-test value is 416.19 bigger than the critical value 2.36. Therefore the model has good fitting degree and the regression equation is significant. The prediction precision of the model is 91.7%, and it suits the converter end-point control online and the fast tapping model request.
引文
[1]王军.中国钢铁统计[J].中国钢铁协会信息统计部,2000-2001
[2]朱满堂,于华财,徐明.钢主要成分冶炼控制生产实践[J].炼钢,2004,18(2):235-246
[3]杨文远,高振滨.转炉溅渣护炉对钢水质量的影响[J].钢铁,2000,19(7):13-16
[4]刘浏.转炉全自动吹炼技术[J].冶金自动化,1999,20(4):1-6
[5]王勇,杨宁川,王承宽.我国转炉炼钢的现状和发展[J].特殊钢.2005,15(4):1-5
[6]刘浏.转炉控制信息与在线检测技术(上)[J].冶金自动化,2000,10(2):5-8
[7]王建军.转炉烟气分析动态控制炼钢技术[J].河南冶金,2004,7(2):3-6
[8]王茂华,汪保平,惠志刚.转炉终点控制技术[J].河南冶金,2004,12(6):6-9
[9]李润生,李延辉,胡学军.神经网络在冶金中的应用[J].钢铁研究,1998,(2):48-50
[10]余志祥.现代转炉炼钢新技术开发、创新与应用[J].中国冶金,2003,19(3):6-11
[11]刘浏.转炉全自动吹炼技术[J].冶金自动化,1999,31(4):1-6
[12]J R Boom.B Shangen,W Raai jen,et al.Developments in Sublane Design and Measurement Techniques at Hoogovens Ijmuiden Plant[J].I&SM,1998,15..25-28
[13]J H Gruner.A new metallurgical insight into BOP steehnaking and improved process control using sublance techniques and bottom gas stirring[J].Ironmaking&Steelmaking,1985,12:31-36
[14]刘浏.转炉控制信息与在线检测技术(下)[J].冶金自动化,2000,45(2):5-8
[15]胡志刚.150t转炉利用炉气分析进行喷溅预报及控制[J].钢铁,2004,47(6):18-20
[16]王建军.转炉烟气分析动态控制炼钢技术[J].河南冶金,2004,22(2):3-6
[17]杜锋译.奥钢联开发不用副枪进行动态控制的新方法[J].上海余属,200,10(1):60-61
[18]Takeshi Takawn.Analysis of converter process variables from exhaust[J].Trans ISIJ,1988,28(1):596-714
[19]副岛利行.转炉吹炼制铁技术[J].神户制钢技报,1986,36:31-35
[20]J Frank H.Improvement of tumdown performance by USe of BOMB tilermocoupleat GRANITE city steel BOF shop[J],stelmaking comference proceedings,1993,76:169-176
[21]S Mika,B Scholkopf,A J Smola et al.Kemel PCA and de-noising in feature spaces[J].Advances Neural Information Processing Systems,2000,11:526-532
[22]Roshan K.Thomas and Ravi S.Sandhu.Conceptual Foundations for a Model of Task-based Authorizations[J].Computer Security Foundations Workshotp Ⅶ,1994.CSFW 7.1994,66-79
[23]张旭日.质谱仪在转炉炼钢终点控制中的应用[J].鞍钢技术,2003,(6):8-11
[24]胡志刚.利用炉气分析进行转炉钢水连续定碳[J].钢铁研究,2003,(3):12-15
[25]Zhang J,Morris A J.Recurrent neural-fuzzy networks for nonlinear process modeling[J].IEEE Trans onNeural Networks,1999,10(2):313-325
[26]李润生,李延辉,胡学军.神经网络在冶金中的应用[J].钢铁研究,1998,20(2):48-50
[27]Haran M T,Menhaj M B.Training feedforward net works with the Marquardt algorithm[J].IEEE TransNeural Network,1994,5(6):989-993
[28]赵弘,周瑞祥,林廷圻.基于LM算法的神经网络监督控制[J].西安交通大学学报,2002,36(5):523-527
[29]柴天佑,谢书明,杜斌,等.基于RBF神经网络的转炉炼钢终点预报[J].中国有色金属学报,1999,9(4):868-872
[30]丁容,刘浏.转炉炼钢过程人工智能静态控制模型[J].钢铁,1997,32(1):22-26
[31]陈淑珍,陈窖.基于COM技术的多媒体监控系统的设计与实现[J].武汉大学学报,2001,(3):377-380
[32]魏立诚,朱桂林.基于DirectShow的视频采集系统的设计与实现[J].计算机工程,2005,(7):230-256
[33]文坤,高胜法.DirectShow程序设计原理及应用[J].计算机系统应用,2006,(5):228-265
[34]陈昱,王博亮,谢杰镇.基于DirectShow的眼前节图像采集系统的设计[J].厦门大学学报(自然科学版),2005,44(4):503-506
[35]武兆雪,夏靖波.基于Direct-Show的多媒体流捕获[J].计算机工程,2006,(10)100-101
[36]王裉.图像测量技术及其应用“电测与仪表”。 2006,(10):100-101
[37]陆其明.DirectShow实务精选[M].北京科海电子出版社,2004,(12):200-250
[38]徐胜荣.计算机图像处理[M].杭州:浙江大学出版社,1990,(14)50-70
[39]何万青,黄铜,沈爱国.基DSP和数字视频技术的图像火焰检测系统[J].中国电力,2000,54(33):64-67
[40]周怀春,娄新生,肖教芳等.炉膛火焰温度场处理试验研究[J].中国电机工程学报,1997,20(1):1-4
[41]卫成业.利用面阵CCD进行火焰温度分布测量[J].热能动力工程,2002,30(1):58-60
[42]李少辉,高岳,高稚允.图像比色法在炉膛火焰温度场实时监测的研究[J].光学技术.2002,(2):145-148
[43]A.Sharan,Light Sensors for BOF Carbon Control in Low Carbon Heats[J].Steelmaking Conference Proceedings.1998,81:337-345
[44]Izumi Nishidate,Yoshihisa Aizu,Hiromichi Mishina.Estimation of melanin and hemoglobin in skin tissue using multiple regression analysis aided by Monte Carlo simulation[J].Journal of Biomedical Optics.2004,4:700-710
[45]QiBo,Chen Hongbin,Ma Jiaguang,Dong Nengli,Regression analysis for wavefront fitting with Zernike polynomials[J].Proceedings of SPIE.2003,180:429-436
[46]刘冬梅,吴伟,黄伟青.顶底复吹转炉冶炼终点钢水成分及温度回归预测分析[J].材料与冶金学报,2003,19(1):3-7
[47]Korol Renee M,Canhan Peter B,Lucas Alexandra R.Multiple regression analysis [J].Biophotonics International.2005,8:47-48
[48]Microsoft Corporation.Microsoft DirectX 9.0 SDK Documentation[M].Microsoft Corporation,2002
[49]Gonzalez R C,Woods R E,Eddins S L.Digital Image Processing Using MATLAB [M].Shaddle River,New Jersey,US:Prentice Hall,2004
[50]徐江荣,胡建人.火焰辐射温度场测量系统黑体炉标定[J].杭州电子工业学院学报,2002,22(1):44-47
[51]费业泰.误差理论与数据处理[M].北京:机械工业出版社,2000
[52]赵琦,陈延如,王昀,等.光强与图像信息在转炉炼钢终点判断中的应用[J].仪器仪表学报,2005,26(8):575-577,580
[53]温宏愿,陈延如,赵琦.利用DirectShow提取转炉炉口火焰图像特征信息[J].华中科技大学学报(自然科学版),2007,35(sl):246-248
[54]徐建华.图象处理与分析[M].北京:科学出版社,1992.34-36
[55]王松桂.线性模型的理论及其应用[M].合肥:安徽教育出版社.1987(9)100-110
[56]张建军,吴晓平.线性回归模型系数岭估计的改进研究[J].海军工程大学学报,2005,17(1):54-57
[57]张玮,文禄勤.线性回归模型的一种有偏估计[J].武汉大学学报,2005,52(3): 281-285
[58]Hoerl A E。 Kennard R W.Ridge regression:biased estimation for non-orthogonal problems[J].Teehnometfies,1970,12:55-67
[59]Hoerl A E,Kennard R W.Ridge regression:applications to nonorthogonal problems[J].Tecbnometrics,1970,12:69-82
[2]朱满堂,于华财,徐明.钢主要成分冶炼控制生产实践[J].炼钢,2004,18(2):235-246
[3]杨文远,高振滨.转炉溅渣护炉对钢水质量的影响[J].钢铁,2000,19(7):13-16
[4]刘浏.转炉全自动吹炼技术[J].冶金自动化,1999,20(4):1-6
[5]王勇,杨宁川,王承宽.我国转炉炼钢的现状和发展[J].特殊钢.2005,15(4):1-5
[6]刘浏.转炉控制信息与在线检测技术(上)[J].冶金自动化,2000,10(2):5-8
[7]王建军.转炉烟气分析动态控制炼钢技术[J].河南冶金,2004,7(2):3-6
[8]王茂华,汪保平,惠志刚.转炉终点控制技术[J].河南冶金,2004,12(6):6-9
[9]李润生,李延辉,胡学军.神经网络在冶金中的应用[J].钢铁研究,1998,(2):48-50
[10]余志祥.现代转炉炼钢新技术开发、创新与应用[J].中国冶金,2003,19(3):6-11
[11]刘浏.转炉全自动吹炼技术[J].冶金自动化,1999,31(4):1-6
[12]J R Boom.B Shangen,W Raai jen,et al.Developments in Sublane Design and Measurement Techniques at Hoogovens Ijmuiden Plant[J].I&SM,1998,15..25-28
[13]J H Gruner.A new metallurgical insight into BOP steehnaking and improved process control using sublance techniques and bottom gas stirring[J].Ironmaking&Steelmaking,1985,12:31-36
[14]刘浏.转炉控制信息与在线检测技术(下)[J].冶金自动化,2000,45(2):5-8
[15]胡志刚.150t转炉利用炉气分析进行喷溅预报及控制[J].钢铁,2004,47(6):18-20
[16]王建军.转炉烟气分析动态控制炼钢技术[J].河南冶金,2004,22(2):3-6
[17]杜锋译.奥钢联开发不用副枪进行动态控制的新方法[J].上海余属,200,10(1):60-61
[18]Takeshi Takawn.Analysis of converter process variables from exhaust[J].Trans ISIJ,1988,28(1):596-714
[19]副岛利行.转炉吹炼制铁技术[J].神户制钢技报,1986,36:31-35
[20]J Frank H.Improvement of tumdown performance by USe of BOMB tilermocoupleat GRANITE city steel BOF shop[J],stelmaking comference proceedings,1993,76:169-176
[21]S Mika,B Scholkopf,A J Smola et al.Kemel PCA and de-noising in feature spaces[J].Advances Neural Information Processing Systems,2000,11:526-532
[22]Roshan K.Thomas and Ravi S.Sandhu.Conceptual Foundations for a Model of Task-based Authorizations[J].Computer Security Foundations Workshotp Ⅶ,1994.CSFW 7.1994,66-79
[23]张旭日.质谱仪在转炉炼钢终点控制中的应用[J].鞍钢技术,2003,(6):8-11
[24]胡志刚.利用炉气分析进行转炉钢水连续定碳[J].钢铁研究,2003,(3):12-15
[25]Zhang J,Morris A J.Recurrent neural-fuzzy networks for nonlinear process modeling[J].IEEE Trans onNeural Networks,1999,10(2):313-325
[26]李润生,李延辉,胡学军.神经网络在冶金中的应用[J].钢铁研究,1998,20(2):48-50
[27]Haran M T,Menhaj M B.Training feedforward net works with the Marquardt algorithm[J].IEEE TransNeural Network,1994,5(6):989-993
[28]赵弘,周瑞祥,林廷圻.基于LM算法的神经网络监督控制[J].西安交通大学学报,2002,36(5):523-527
[29]柴天佑,谢书明,杜斌,等.基于RBF神经网络的转炉炼钢终点预报[J].中国有色金属学报,1999,9(4):868-872
[30]丁容,刘浏.转炉炼钢过程人工智能静态控制模型[J].钢铁,1997,32(1):22-26
[31]陈淑珍,陈窖.基于COM技术的多媒体监控系统的设计与实现[J].武汉大学学报,2001,(3):377-380
[32]魏立诚,朱桂林.基于DirectShow的视频采集系统的设计与实现[J].计算机工程,2005,(7):230-256
[33]文坤,高胜法.DirectShow程序设计原理及应用[J].计算机系统应用,2006,(5):228-265
[34]陈昱,王博亮,谢杰镇.基于DirectShow的眼前节图像采集系统的设计[J].厦门大学学报(自然科学版),2005,44(4):503-506
[35]武兆雪,夏靖波.基于Direct-Show的多媒体流捕获[J].计算机工程,2006,(10)100-101
[36]王裉.图像测量技术及其应用“电测与仪表”。 2006,(10):100-101
[37]陆其明.DirectShow实务精选[M].北京科海电子出版社,2004,(12):200-250
[38]徐胜荣.计算机图像处理[M].杭州:浙江大学出版社,1990,(14)50-70
[39]何万青,黄铜,沈爱国.基DSP和数字视频技术的图像火焰检测系统[J].中国电力,2000,54(33):64-67
[40]周怀春,娄新生,肖教芳等.炉膛火焰温度场处理试验研究[J].中国电机工程学报,1997,20(1):1-4
[41]卫成业.利用面阵CCD进行火焰温度分布测量[J].热能动力工程,2002,30(1):58-60
[42]李少辉,高岳,高稚允.图像比色法在炉膛火焰温度场实时监测的研究[J].光学技术.2002,(2):145-148
[43]A.Sharan,Light Sensors for BOF Carbon Control in Low Carbon Heats[J].Steelmaking Conference Proceedings.1998,81:337-345
[44]Izumi Nishidate,Yoshihisa Aizu,Hiromichi Mishina.Estimation of melanin and hemoglobin in skin tissue using multiple regression analysis aided by Monte Carlo simulation[J].Journal of Biomedical Optics.2004,4:700-710
[45]QiBo,Chen Hongbin,Ma Jiaguang,Dong Nengli,Regression analysis for wavefront fitting with Zernike polynomials[J].Proceedings of SPIE.2003,180:429-436
[46]刘冬梅,吴伟,黄伟青.顶底复吹转炉冶炼终点钢水成分及温度回归预测分析[J].材料与冶金学报,2003,19(1):3-7
[47]Korol Renee M,Canhan Peter B,Lucas Alexandra R.Multiple regression analysis [J].Biophotonics International.2005,8:47-48
[48]Microsoft Corporation.Microsoft DirectX 9.0 SDK Documentation[M].Microsoft Corporation,2002
[49]Gonzalez R C,Woods R E,Eddins S L.Digital Image Processing Using MATLAB [M].Shaddle River,New Jersey,US:Prentice Hall,2004
[50]徐江荣,胡建人.火焰辐射温度场测量系统黑体炉标定[J].杭州电子工业学院学报,2002,22(1):44-47
[51]费业泰.误差理论与数据处理[M].北京:机械工业出版社,2000
[52]赵琦,陈延如,王昀,等.光强与图像信息在转炉炼钢终点判断中的应用[J].仪器仪表学报,2005,26(8):575-577,580
[53]温宏愿,陈延如,赵琦.利用DirectShow提取转炉炉口火焰图像特征信息[J].华中科技大学学报(自然科学版),2007,35(sl):246-248
[54]徐建华.图象处理与分析[M].北京:科学出版社,1992.34-36
[55]王松桂.线性模型的理论及其应用[M].合肥:安徽教育出版社.1987(9)100-110
[56]张建军,吴晓平.线性回归模型系数岭估计的改进研究[J].海军工程大学学报,2005,17(1):54-57
[57]张玮,文禄勤.线性回归模型的一种有偏估计[J].武汉大学学报,2005,52(3): 281-285
[58]Hoerl A E。 Kennard R W.Ridge regression:biased estimation for non-orthogonal problems[J].Teehnometfies,1970,12:55-67
[59]Hoerl A E,Kennard R W.Ridge regression:applications to nonorthogonal problems[J].Tecbnometrics,1970,12:69-82
© 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 |