焦炭质量预测与优化配比算法的研究
|
摘要
随着国民经济的迅速发展,钢铁的需求量逐年上升,用于炼钢的冶金焦的需求量也迅速增大,如何根据现有的煤资源来达到预期的焦炭指标,稳定焦炭质量,并使成本最小是焦化行业追求的目标。
炼焦配煤是一个复杂的过程,但对于一个具体的焦化厂,在一段稳定生产时期内,炼焦工艺、加热制度等基本不变,焦炉设备状态也基本稳定,这些基本不变因素对焦炭质量的影响也基本相同或变化不大,因此影响焦炭质量的因素便可缩小到配合煤的质量,而配合煤的性质又是由参加配合的单种煤的性质与配比决定的,调整配合煤种和配比,就可控制焦炭质量,优选配合煤种和配比就可降低炼焦用煤成本。
本文在国内外配煤理论与方法及焦炭质量预测研究现状的基础上,根据某焦化厂近两年的生产数据,分析单种煤到配合煤的预测,发现配合煤的黏结指数和胶质层最大厚度不具有加和性,加权平均误差很大。对单种煤进行模糊聚类后,对同一类的单种煤进行加权平均,然后再利用历史数据对未来的数据进行预测,预测的结果表明此方法误差比简单的加权平均的预测精度较高,证明该预测方法的可行性。对焦炭质量的预测采用线性的回归分析、稳健回归和非线性的神经网络与支持向量机的方法,在预测分析的同时进行了试验分析。分析结果表明,支持向量机的预测精度比前三种方法高,灰分、硫分、M40、M10、CRI、CSR的平均误差分别为0.0719、0.0364、0.5348、0.1001、0.6440、1.0681。证明配煤和炼焦过程的复杂关系可以用基于统计理论的支持向量机来正确描述,为进一步提高焦炭质量预测的准确性和科学性提供了一种新方法。在以上理论的基础上,引入遗传算法,将遗传算法和支持向量机相结合,为计算单种煤的配比提供了一种新的方法。
With the rapid development of the national economy, the demand of steel is increasing year after year and the metallurgical coke for steel-making is also increasing rapidly. How to achieve desired targets of coke and make the coke's quality stable and minimize the cost using the existing coal resources is coking industries' goal.
Coking coal is a complex process, but to a specific coking factory, its coking process and heating system will remain basically unchanged in a stable period of production, the state of coke oven equipment is also stable. These essentially unchanged factors have the same influence on the quality of coke or have changed little. Thereby the factors that affect the quality of coke can be reduced to the quality of matching coal, while the property of matching coal is decided by every single coal's property and ratio. Accordingly, adjusting the matching coal and radio can control the quality of coke and the optimization with matching and ratio can lower the cost.
In this paper, according to some factories' production data in recent two years, after analyzing a single coal to matching coal's forecast on the basis of theory and method on matching coal at home and abroad, it is discovered that the felting exponent of matching coal and the max thickness of gelatine don't have weigh and the weighed average error is large. After the fuzzy clustering en the single coal, calculate the weighted average of the single coal of the same type, and then use historical data to predict the future data. The forecasting results showed that this method is better than simple weighted average forecast that the method is feasible. On coke quality forecasts using linear regression analysis, robust regression and non-linear Neural Network and Support Vector Machine method, the predictive analysis of the test is carried out at the same time. The results show that the prediction accuracy of SVM is higher than the previous three methods. The average errors of ash, sulfur, M40, M10, CRI, CSR are 0.0719, 0.0364, 0.5348, 0.1001, 0.6440, 1.0681 respectively. It is proved that the complex relationship of coking and coal blending can be correctly described by the Support Vector Machine based on the statistical theory, which provides a new method for further improving the scientificity and accuracy of the forecasting of coke's quality. On the basis of the above theory, I introduce the genetic algorithm, and combine the genetic algorithms with support vector machines, which provides a new approach for the calculating the ratio of single coal.
炼焦配煤是一个复杂的过程,但对于一个具体的焦化厂,在一段稳定生产时期内,炼焦工艺、加热制度等基本不变,焦炉设备状态也基本稳定,这些基本不变因素对焦炭质量的影响也基本相同或变化不大,因此影响焦炭质量的因素便可缩小到配合煤的质量,而配合煤的性质又是由参加配合的单种煤的性质与配比决定的,调整配合煤种和配比,就可控制焦炭质量,优选配合煤种和配比就可降低炼焦用煤成本。
本文在国内外配煤理论与方法及焦炭质量预测研究现状的基础上,根据某焦化厂近两年的生产数据,分析单种煤到配合煤的预测,发现配合煤的黏结指数和胶质层最大厚度不具有加和性,加权平均误差很大。对单种煤进行模糊聚类后,对同一类的单种煤进行加权平均,然后再利用历史数据对未来的数据进行预测,预测的结果表明此方法误差比简单的加权平均的预测精度较高,证明该预测方法的可行性。对焦炭质量的预测采用线性的回归分析、稳健回归和非线性的神经网络与支持向量机的方法,在预测分析的同时进行了试验分析。分析结果表明,支持向量机的预测精度比前三种方法高,灰分、硫分、M40、M10、CRI、CSR的平均误差分别为0.0719、0.0364、0.5348、0.1001、0.6440、1.0681。证明配煤和炼焦过程的复杂关系可以用基于统计理论的支持向量机来正确描述,为进一步提高焦炭质量预测的准确性和科学性提供了一种新方法。在以上理论的基础上,引入遗传算法,将遗传算法和支持向量机相结合,为计算单种煤的配比提供了一种新的方法。
With the rapid development of the national economy, the demand of steel is increasing year after year and the metallurgical coke for steel-making is also increasing rapidly. How to achieve desired targets of coke and make the coke's quality stable and minimize the cost using the existing coal resources is coking industries' goal.
Coking coal is a complex process, but to a specific coking factory, its coking process and heating system will remain basically unchanged in a stable period of production, the state of coke oven equipment is also stable. These essentially unchanged factors have the same influence on the quality of coke or have changed little. Thereby the factors that affect the quality of coke can be reduced to the quality of matching coal, while the property of matching coal is decided by every single coal's property and ratio. Accordingly, adjusting the matching coal and radio can control the quality of coke and the optimization with matching and ratio can lower the cost.
In this paper, according to some factories' production data in recent two years, after analyzing a single coal to matching coal's forecast on the basis of theory and method on matching coal at home and abroad, it is discovered that the felting exponent of matching coal and the max thickness of gelatine don't have weigh and the weighed average error is large. After the fuzzy clustering en the single coal, calculate the weighted average of the single coal of the same type, and then use historical data to predict the future data. The forecasting results showed that this method is better than simple weighted average forecast that the method is feasible. On coke quality forecasts using linear regression analysis, robust regression and non-linear Neural Network and Support Vector Machine method, the predictive analysis of the test is carried out at the same time. The results show that the prediction accuracy of SVM is higher than the previous three methods. The average errors of ash, sulfur, M40, M10, CRI, CSR are 0.0719, 0.0364, 0.5348, 0.1001, 0.6440, 1.0681 respectively. It is proved that the complex relationship of coking and coal blending can be correctly described by the Support Vector Machine based on the statistical theory, which provides a new method for further improving the scientificity and accuracy of the forecasting of coke's quality. On the basis of the above theory, I introduce the genetic algorithm, and combine the genetic algorithms with support vector machines, which provides a new approach for the calculating the ratio of single coal.
引文
铩颷1]唐莉.炼焦用单种煤的特性研究及其选择,鞍钢技术,2002,1,13-16
[2]孟超慧,吕铮.焦炭质量对高炉生产的影响,鞍钢技术,2004,5,9-12
[3]郝洪洲.配煤参数与焦炭质量,煤化工,2001,4,20-22
[4]周师庸,周淑仪.烟煤容纳惰性物质能力.炼焦化学,1984,6:4-8
[5]谢海深,刘永新,孟军波,吕庆.焦炭质量预测模型的研究,煤炭转化,2006,29(3),54-57
[6]谢海深,孟军波,刘永新,吕庆.配煤优化模型及其专家系统的设计,计算机与应用化学,2006,23(5),621-624
[7]刘洪春,徐海平,刘宏,高光良.炼焦配煤优化系统在炼焦生产中的应用,燃料与化工,2005,36(6),6-9
[8]谢海深,刘永新,吕庆,孟军波.焦炭质量预测模型,东北大学学报,2007,28(3),373-377
[9]Hara Y,Sakawa M,Sakurai Y1.The assessment of coke quality with particularemphasis on sampling technique.Canada:McMaster University,1980
[10]Valia H S1 Prediction of coke strength after reaction with CO2 from coal analysesat inland steel company,I&SM,1989,(5),77-87
[11]Toshimitsu R,Ishiguro M.Development of control method of coke strength afterCO2 reaction.53rd Ironmaking Conference Proceedings.Illinois:Chicago,1994,71-78
[12]Angeleri R.Predicting coke strength after reaction of blend in the sole-heatedoven.57th Ironmaking Conference Proceedings.Canada:Toronto,1998,1061-1073
[13]周师庸,周淑仪,陈爱国.酒钢焦炭质量预测方法的研究,燃料与化工,1999,21(4)
[14]王光辉,范程.焦炭质量预测方法的研究,武汉科技大学学报,2007,30(1),38-40
[15]张士金.焦炭热反应性的研究,本钢技术,2006,3,24-26
[16]张群,吴信慈,冯安祖,史美仁.宝钢焦炭质量预测模型Ⅰ影响焦炭热性质的因素,燃料化学学报,2002,30(2),113-117
铩颷17]A.I.Gordienko,A.R.Davidzon,V.I.Chalenko.Influence of the metamorphicstate of coal batch on the coke quality(CRI,CSR).Coke and Chemistry,50(5)2007,117-123
[18]姚昭章.炼焦学.冶金工业出版社,2005
[19]申明新.中国炼焦煤的资源与利用,化学工业出版社,2007
[20]张放民.线性规划优化配煤,煤气与热力,2001,21(2),138-139
[21]陶著.煤化学,冶金工业出版社,1984
[22]徐君,赵峻国,周淑仪,周师庸.近代煤炭质量检控的首要指标--反射率,冶金能源,2002,21(1),55-58
[23]姚伯元,李德谨,马学刚.各类型混煤在炼焦配煤中的作用,燃料与化工,2007,38(6),1-6
[24]虞继舜.煤化学,北京:冶金工业出版社.2003
[25]张有芝.降低焦炭灰分提高焦炭质量,山西冶金,,2007,105(1),22-23
[26]宋旗跃,白向飞,于景峰.岩相分析在混煤鉴别与控制中的应用,燃料与化工,2004,31(1),130-133
[27]才让加.化学数据的一元线性回归分析,青海师范大学学报,2005,2,13-15
[28]孙宝,刘玲.线性回归模型预测借阅量,现代情报,2007,9,159-162
[29]王惠文,孟洁.多元线性回归的预测建模方法,北京航空航天大学学报,2007,33(4),500-504
[30]薛素静,上官同英.多元线性回归算法的研究和应用,水利电力机械,2007,29(5),59-60
[31]田胜龙,佟胤铮.多元线性回归在地下水资源评价中的应用,东北水利水电,2007,24(3),23-24
[32]陈艳国.回归预测模型的稳健性分析,西部探矿工程,2006,118(2),177-179
[33]王新军,黄守坤.预测型稳健回归模型及其实证分析,统计研究,2004,12,42-45
[34]姚宜斌,陶本藻,施闯.稳健回归分析及其应用研究,大地测量与地球动力学,2002,22(2),16-19
[35]周莉.岩土抗剪强度参数模糊稳健回归分析,黑龙江科技学院学报,2007,17(2),90-93
[36]柳进,唐降龙,于继来.基于稳健回归的电网高峰负荷预测模型应用,数理统计与管理,2005,29(5),56-59
[37]周振民,刘荻.基于Matlab的人工神经网络用水量预测模型,中国农村水利水电, 2007,4,45-47
铩颷38]刘解放,侯振雨,吴亮。支持向量机在模式识别和回归模型中的应用,河南科技学院学报,2007,35(4),89-92
[39]汪灵枝,吴建生,吴春梅。偏最小二乘回归的贝叶斯正则化神经网络集成模型在证券分析预测中的应用,数学的实践与认识,2007,14(37),197-204
[40]郭庆武.Matlab神经网络工具箱及其在软测量建模中的应用,东南大学学报,2003,33,209-212
[41]李栋,王洪礼.城市生活用水量的支持向量回归预测,天津大学学报 2006,8(1),64-66
[42]孔繁钰,徐瑞华,姚胜永.交通量的支持向量回归预测及参数选择研究,计算机工程 2007,33(5),20-22
[43]马庆元.中国炼焦煤资源的分布特征,煤炭科学技术,2004,32(3),63-66
[44]V.Vapnik.Statistical Learning Theory.Wiley,New York,NY,1998
[45]田景文,高美娟.人工神经网络算法研究及应用,北京理工大学出版,2006
[46]Nello Cristianini,John Shawe-Taylor.An Introdection to Support Vector Machinesand other Kernel_based Learning Methods.Publishing House of ElectronicsIndustry,2000
[47]李寿林,李秀萍,张鹰.支持向量机回归法在天线设计中的应用,电子器件,2007,30(4),1285-1288
[48]C.-J.Lin,R.C.Weng,and S.S.Keerthi.Trust region Newton method forlarge-scale logistic regression,Technical report,2007.
[49]C.-W.Hsu,C.-J.Lin.A comparison of methods for multi-class support vectormachines,IEEE Transactions on Neural Networks,13(2),2002
[50]高新波.模糊聚类分析及其应用,西安电子科技大学出版社,2004
[51]许义海.一种快速寻优的新型改进遗传算法,中山大学学报,2006,45(2),36-39
[52]张兵.基于L-M优化算法的BP神经网络的作物需水量预测模型,农业工程学报,2004,(6).
[53]刘璐,汪传生,徐敏奎.VB和MATLAB在混炼胶粘度预测神经网络专家系统中的研究,特种橡胶制品,2004,25(3),41-44
[54]冯莉,李巨,邓云华.VB与MATLAB的混合编程,软件技术,2005,24(5),110-112
[55]单晓云,赵树果,刘永新.基于神经网络的焦炭质量预测模型,选煤技术,2005, 2,1-4
铩颷56]王小平,曹立明。遗传算法-理论、应用与软件实现,西安交通大学出版社,2002
[57]陆亿红,柳红,基于整数编码和自适应遗传算法的自动组卷,计算机工程,2005,31(23),232-233
[2]孟超慧,吕铮.焦炭质量对高炉生产的影响,鞍钢技术,2004,5,9-12
[3]郝洪洲.配煤参数与焦炭质量,煤化工,2001,4,20-22
[4]周师庸,周淑仪.烟煤容纳惰性物质能力.炼焦化学,1984,6:4-8
[5]谢海深,刘永新,孟军波,吕庆.焦炭质量预测模型的研究,煤炭转化,2006,29(3),54-57
[6]谢海深,孟军波,刘永新,吕庆.配煤优化模型及其专家系统的设计,计算机与应用化学,2006,23(5),621-624
[7]刘洪春,徐海平,刘宏,高光良.炼焦配煤优化系统在炼焦生产中的应用,燃料与化工,2005,36(6),6-9
[8]谢海深,刘永新,吕庆,孟军波.焦炭质量预测模型,东北大学学报,2007,28(3),373-377
[9]Hara Y,Sakawa M,Sakurai Y1.The assessment of coke quality with particularemphasis on sampling technique.Canada:McMaster University,1980
[10]Valia H S1 Prediction of coke strength after reaction with CO2 from coal analysesat inland steel company,I&SM,1989,(5),77-87
[11]Toshimitsu R,Ishiguro M.Development of control method of coke strength afterCO2 reaction.53rd Ironmaking Conference Proceedings.Illinois:Chicago,1994,71-78
[12]Angeleri R.Predicting coke strength after reaction of blend in the sole-heatedoven.57th Ironmaking Conference Proceedings.Canada:Toronto,1998,1061-1073
[13]周师庸,周淑仪,陈爱国.酒钢焦炭质量预测方法的研究,燃料与化工,1999,21(4)
[14]王光辉,范程.焦炭质量预测方法的研究,武汉科技大学学报,2007,30(1),38-40
[15]张士金.焦炭热反应性的研究,本钢技术,2006,3,24-26
[16]张群,吴信慈,冯安祖,史美仁.宝钢焦炭质量预测模型Ⅰ影响焦炭热性质的因素,燃料化学学报,2002,30(2),113-117
铩颷17]A.I.Gordienko,A.R.Davidzon,V.I.Chalenko.Influence of the metamorphicstate of coal batch on the coke quality(CRI,CSR).Coke and Chemistry,50(5)2007,117-123
[18]姚昭章.炼焦学.冶金工业出版社,2005
[19]申明新.中国炼焦煤的资源与利用,化学工业出版社,2007
[20]张放民.线性规划优化配煤,煤气与热力,2001,21(2),138-139
[21]陶著.煤化学,冶金工业出版社,1984
[22]徐君,赵峻国,周淑仪,周师庸.近代煤炭质量检控的首要指标--反射率,冶金能源,2002,21(1),55-58
[23]姚伯元,李德谨,马学刚.各类型混煤在炼焦配煤中的作用,燃料与化工,2007,38(6),1-6
[24]虞继舜.煤化学,北京:冶金工业出版社.2003
[25]张有芝.降低焦炭灰分提高焦炭质量,山西冶金,,2007,105(1),22-23
[26]宋旗跃,白向飞,于景峰.岩相分析在混煤鉴别与控制中的应用,燃料与化工,2004,31(1),130-133
[27]才让加.化学数据的一元线性回归分析,青海师范大学学报,2005,2,13-15
[28]孙宝,刘玲.线性回归模型预测借阅量,现代情报,2007,9,159-162
[29]王惠文,孟洁.多元线性回归的预测建模方法,北京航空航天大学学报,2007,33(4),500-504
[30]薛素静,上官同英.多元线性回归算法的研究和应用,水利电力机械,2007,29(5),59-60
[31]田胜龙,佟胤铮.多元线性回归在地下水资源评价中的应用,东北水利水电,2007,24(3),23-24
[32]陈艳国.回归预测模型的稳健性分析,西部探矿工程,2006,118(2),177-179
[33]王新军,黄守坤.预测型稳健回归模型及其实证分析,统计研究,2004,12,42-45
[34]姚宜斌,陶本藻,施闯.稳健回归分析及其应用研究,大地测量与地球动力学,2002,22(2),16-19
[35]周莉.岩土抗剪强度参数模糊稳健回归分析,黑龙江科技学院学报,2007,17(2),90-93
[36]柳进,唐降龙,于继来.基于稳健回归的电网高峰负荷预测模型应用,数理统计与管理,2005,29(5),56-59
[37]周振民,刘荻.基于Matlab的人工神经网络用水量预测模型,中国农村水利水电, 2007,4,45-47
铩颷38]刘解放,侯振雨,吴亮。支持向量机在模式识别和回归模型中的应用,河南科技学院学报,2007,35(4),89-92
[39]汪灵枝,吴建生,吴春梅。偏最小二乘回归的贝叶斯正则化神经网络集成模型在证券分析预测中的应用,数学的实践与认识,2007,14(37),197-204
[40]郭庆武.Matlab神经网络工具箱及其在软测量建模中的应用,东南大学学报,2003,33,209-212
[41]李栋,王洪礼.城市生活用水量的支持向量回归预测,天津大学学报 2006,8(1),64-66
[42]孔繁钰,徐瑞华,姚胜永.交通量的支持向量回归预测及参数选择研究,计算机工程 2007,33(5),20-22
[43]马庆元.中国炼焦煤资源的分布特征,煤炭科学技术,2004,32(3),63-66
[44]V.Vapnik.Statistical Learning Theory.Wiley,New York,NY,1998
[45]田景文,高美娟.人工神经网络算法研究及应用,北京理工大学出版,2006
[46]Nello Cristianini,John Shawe-Taylor.An Introdection to Support Vector Machinesand other Kernel_based Learning Methods.Publishing House of ElectronicsIndustry,2000
[47]李寿林,李秀萍,张鹰.支持向量机回归法在天线设计中的应用,电子器件,2007,30(4),1285-1288
[48]C.-J.Lin,R.C.Weng,and S.S.Keerthi.Trust region Newton method forlarge-scale logistic regression,Technical report,2007.
[49]C.-W.Hsu,C.-J.Lin.A comparison of methods for multi-class support vectormachines,IEEE Transactions on Neural Networks,13(2),2002
[50]高新波.模糊聚类分析及其应用,西安电子科技大学出版社,2004
[51]许义海.一种快速寻优的新型改进遗传算法,中山大学学报,2006,45(2),36-39
[52]张兵.基于L-M优化算法的BP神经网络的作物需水量预测模型,农业工程学报,2004,(6).
[53]刘璐,汪传生,徐敏奎.VB和MATLAB在混炼胶粘度预测神经网络专家系统中的研究,特种橡胶制品,2004,25(3),41-44
[54]冯莉,李巨,邓云华.VB与MATLAB的混合编程,软件技术,2005,24(5),110-112
[55]单晓云,赵树果,刘永新.基于神经网络的焦炭质量预测模型,选煤技术,2005, 2,1-4
铩颷56]王小平,曹立明。遗传算法-理论、应用与软件实现,西安交通大学出版社,2002
[57]陆亿红,柳红,基于整数编码和自适应遗传算法的自动组卷,计算机工程,2005,31(23),232-233