基于粗糙集的转炉炼钢知识发现及终点控制模型研究
|
摘要
转炉炼钢是一个化学反应速度快、影响因素多、过程复杂的多元多相高温物理化学过程，其控制核心是对冶炼终点钢水的温度和碳含量进行准确控制。在转炉炼钢生产过程中，提高转炉冶炼终点控制的准确性可以有效缩短冶炼周期，提高炉衬寿命，减少钢铁料消耗，进而显著改善和稳定钢水质量，降低生产成本，提高转炉生产率，是炼钢生产过程中增强企业竞争力的一个重要途径。
目前，国内大多数钢铁企业的转炉炼钢终点控制还是依据现场操作人员的生产操作经验进行的，而生产操作经验知识的获取是通过现场生产总结和对生产控制数据的简单统计分析得到。由于转炉炼钢生产现场技术人员、操作人员之间素质参差不齐，实际生产中的工况条件又很复杂，使得仅靠人工经验和简单统计分析得到的转炉冶炼知识进行的终点控制稳定性、准确性不能满足生产要求。目前，基于人工智能方法的知识发现已广泛用于知识发现的各个领域，并取得了比较明显的应用效果，但在转炉炼钢领域的研究尚处于起步阶段。转炉炼钢生产具有过程冶炼机理复杂、反应影响因素众多，冶炼过程采集的数据信息具有多变量、非线性、高噪音的特征，因此，探索一种能够适应转炉炼钢生产过程的复杂性特征，实现转炉炼钢生产知识的发现方法，并在此基础上，形成一套适用于转炉炼钢过程知识发现和冶炼终点控制的模型系统，在理论和应用方面都具有重要的意义。
针对转炉炼钢知识发现和终点控制的特点，本文通过对粗糙集理论方法和人工神经网络方法的分析研究，建立了基于粗糙集理论方法的转炉炼钢知识发现模型和粗糙集-神经网络终点控制模型，实现转炉炼钢生产知识的自动获取和转炉炼钢终点控制方法的优化。其中，基于粗糙集方法的转炉炼钢知识发现模型通过对转炉炼钢生产数据进行清洗、标准化、离散等方式的数据预处理，以转炉炼钢生产重要影响因素作为知识发现的条件属性，以转炉冶炼终点的钢水碳含量和钢水温度作为知识发现的决策属性，采用粗糙集理论方法实现转炉炼钢知识发现的有效属性约简，并结合关联规则提取算法实现转炉炼钢知识的发现和规则提取；基于粗糙集-神经网络的转炉炼钢终点控制模型是结合粗糙集理论和神经网络理论的方法特点，以粗糙集理论方法确定出对决策属性集有重要影响的最小条件属性集作为神经网络的输入条件，有效简化网络结构，提高神经网络模型的适应性、准确性及计算效率。同时，运用面向对象和图形化建模、可视化技术，以适用性、灵活性及可靠性为设计原则，基于Windows开发平台，选用Microsoft的VisualBasic6.0编程实现基于粗糙集的转炉炼钢知识发现及终点控制模型系统的开发。
以新余210t转炉炼钢厂生产工艺和数据信息进行知识发现和终点控制的数值实验，结果表明：基于粗糙集方法的转炉炼钢知识发现模型可以实现知识发现属性的有效约简，同时，采用最小规则支持度和信任度的规则提取算法，可以发现数据中隐藏的知识规则，实现转炉炼钢知识的自动获取；在转炉炼钢知识发现过程中，随着训练数据集的增大，提取出来的知识规则数目相应增多，但知识规则预测的命中率并不一定提高，且随着训练数据集的增大，系统的运算效率会降低，因此，训练集的数据量大小和训练集的代表性对粗糙集转炉炼钢知识发现有着重要的影响；粗糙集转炉炼钢知识发现模型随着规则支持度和信任度的增加，知识规则预测的精确性也越高，发现的有效知识规则数量会降低，但知识的覆盖面会应知识条件的约束范围狭小而显著降低，因此，应在实验的基础上选取较为合理的参数值，不能一味的追求较大的规则支持度和信任度；粗糙集-神经网络模型的输入层结点属性是由基于粗糙集模型确定的对转炉冶炼终点钢水的碳含量和温度有重要影响的因素作为终点预测模型输入参数，因此，相对于常规转炉神经网络终点预测模型，减少了输入层和隐含层的的结点数目，增加了模型网络结构表达的针对性，有效提高模型的计算效率和计算准确性。
因此，本文是针对复杂转炉炼钢过程知识发现与终点控制难题，引入粗糙集理论方法，建立基于粗糙集的转炉炼钢知识发现模型，以及粗糙集-神经网络模型终点预测模型；并以面向对象方法开发了相应的模型系统；以具体炼钢转炉生产过程数据进行了方法的验证及应用测试，表明了方法及系统的有效性。研究成果为转炉炼钢知识发现、终点控制优化等问题研究和生产控制提供了新方法和新手段。
BOF steelmaking is a complicated, multi-component, multi-phase and hightemperature physiochemical process with fast chemical reaction rate and manyinfluencing factors. The control core of the process is to control the endpointtemperature and carbon content of molten steel accurately. During the BOF steelmakingprocess, improving the accuracy of the endpoint control can reduce the tap-to-tap time,prolong the life of furnace lining, reduce the consumption of steel material, improve andstabilize the steel quality, reduce production costs and improve the BOF productivitysignificantly. Thereby, it is an important way to increase the competitiveness ofsteelmaking enterprises.
For now, the endpoint control of BOF steelmaking seriously relies on the engineersand site operators’ experiential knowledge in the majority of domestic steelmakingplants. And the experiential knowledge is mainly acquired by summarizing theexperiences and statistically analyzing the operational data simply. Due to the unevenqualities of the situ technicians and operators and the complexity of the workingconditions for actual steelmaking, the stability and accuracy of the endpoint control byhuman experience and simple statistical analysis can not meet the productionrequirements. Currently, the knowledge discovery based on artificial intelligence hasbeen widely used in various areas, and has got very obviously good results in practicalapplication. However, this research is still in its infancy in the field of BOF steelmaking.The production process of BOF steelmaking which has a complex smelting mechanismis influenced by many factors. The data collected in the smelting process ismultivariable, nonlinear and much high noisy. Therefore, to explore a discoveringmethod which can adapt to the complex characteristics of BOF steelmaking process anddiscover the converter steelmaking production knowledge and setup a system model forknowledge discovering and endpoint controlling have an important significance intheory and application.
For the characteristics of BOF steelmaking knowledge discovery and endpointcontrol, a BOF steelmaking knowledge discovery model and a rough set-neuralnetwork endpoint control model are established based on the rough set theory andneural network analysis. Using the proposed models, the BOF steelmaking productionknowledge can be acquired automatically and the BOF endpoint control method can be optimized. For the rough set-based BOF steelmaking knowledge discovery model, theproduction data can be preprocessed by cleaning, standardizing and straggling. Theimportant influencing factors of BOF steelmaking are served as the knowledgediscovery condition attribute and the molten steel carbon content and molten steeltemperature of BOF smelting endpoint are served as the knowledge discovery decisionattribute. Combined the association rules extract algorithm, the rough set theory methodis used to realize the BOF steelmaking knowledge discovery attribute reduction. TheBOF endpoint control model based on rough set-neural network combined withmethodological characteristics of rough set theory and neural network theory. Theminimum condition attribute set determined by rough set theory method is served as theinput of the neural network conditions and has a major impact on the decision attributeset. The model can effectively simplify the network structure and improve theadaptability, accuracy and computational efficiency of the neural network model. Then,using object-oriented graphical modeling technology, visualization technology and theoptional Microsoft's Visual Basic6.0programming technology, a BOF steelmakingknowledge discovery and endpoint control system model is developed. It is much moreadaptable, flexible and reliable.
The numerical experiments for knowledge discovery and endpoint control areperformed based on the Xinyu210t BOF steelmaking plant production process and datainformation. The results show that: BOF steelmaking knowledge discovery model basedon rough set method could achieve effective reduction of knowledge discoveryproperties. At the same time, the rule extraction algorithm which uses the minimum rulesupport and confidence can find knowledge rules hidden in the data and achieve theautomatic acquisition of BOF steelmaking knowledge. In BOF steelmaking knowledgediscovery process, with the increase of training data set, the number of knowledge rulesextracted increases correspondingly. However, the hit rate predicted by the knowledgerules does not necessarily improve and the operational efficiency of the system willreduce. Therefore, the data size of the training set and the representativeness of thetraining data have important impact on the rough set BOF steelmaking knowledgediscovery. With the increase of rule support and confidence, the predictive accuracy ofthe model knowledge rules become higher and the number of effective knowledge ruleswill reduce, but the coverage of knowledge should be significantly reduced withconstraint range narrow of knowledge conditions. Therefore, more reasonable parametervalues should be selected based on experiments and we should not just pursue of the larger rules support and trust. The input layer node propertie of rough set-nervenetwork model is that the input parameters of the end point prediction model aredetermined by analyzing the factors which have major impact on the endpoint of thesmelting steel endpoint of the carbon content and the temperature of molten steel basedon rough set model. Therefore, related to the conventional BOF neural networkendpoint prediction model, the number of nodes of input layer and hidden layer isreduced and the pertinence of the model network structure expression is increased. Also,the computational efficiency and accuracy of the model is improved effectively.
Aiming at the complex BOF steelmaking process knowledge and endpoint controlproblem, the BOF steelmaking knowledge discovery model based on rough set and therough set-neural network model endpoint prediction model are established throughintroducing the rough set theory in this paper. And, model system based onobject-oriented method is developed. Method validation and practical application whichindicate the effectiveness of method and system are achieved by analyzing the specificBOF steelmaking production process data. Research results provide new methods andmeans for the BOF steelmaking knowledge discovery, end control optimization andproduction control.
目前，国内大多数钢铁企业的转炉炼钢终点控制还是依据现场操作人员的生产操作经验进行的，而生产操作经验知识的获取是通过现场生产总结和对生产控制数据的简单统计分析得到。由于转炉炼钢生产现场技术人员、操作人员之间素质参差不齐，实际生产中的工况条件又很复杂，使得仅靠人工经验和简单统计分析得到的转炉冶炼知识进行的终点控制稳定性、准确性不能满足生产要求。目前，基于人工智能方法的知识发现已广泛用于知识发现的各个领域，并取得了比较明显的应用效果，但在转炉炼钢领域的研究尚处于起步阶段。转炉炼钢生产具有过程冶炼机理复杂、反应影响因素众多，冶炼过程采集的数据信息具有多变量、非线性、高噪音的特征，因此，探索一种能够适应转炉炼钢生产过程的复杂性特征，实现转炉炼钢生产知识的发现方法，并在此基础上，形成一套适用于转炉炼钢过程知识发现和冶炼终点控制的模型系统，在理论和应用方面都具有重要的意义。
针对转炉炼钢知识发现和终点控制的特点，本文通过对粗糙集理论方法和人工神经网络方法的分析研究，建立了基于粗糙集理论方法的转炉炼钢知识发现模型和粗糙集-神经网络终点控制模型，实现转炉炼钢生产知识的自动获取和转炉炼钢终点控制方法的优化。其中，基于粗糙集方法的转炉炼钢知识发现模型通过对转炉炼钢生产数据进行清洗、标准化、离散等方式的数据预处理，以转炉炼钢生产重要影响因素作为知识发现的条件属性，以转炉冶炼终点的钢水碳含量和钢水温度作为知识发现的决策属性，采用粗糙集理论方法实现转炉炼钢知识发现的有效属性约简，并结合关联规则提取算法实现转炉炼钢知识的发现和规则提取；基于粗糙集-神经网络的转炉炼钢终点控制模型是结合粗糙集理论和神经网络理论的方法特点，以粗糙集理论方法确定出对决策属性集有重要影响的最小条件属性集作为神经网络的输入条件，有效简化网络结构，提高神经网络模型的适应性、准确性及计算效率。同时，运用面向对象和图形化建模、可视化技术，以适用性、灵活性及可靠性为设计原则，基于Windows开发平台，选用Microsoft的VisualBasic6.0编程实现基于粗糙集的转炉炼钢知识发现及终点控制模型系统的开发。
以新余210t转炉炼钢厂生产工艺和数据信息进行知识发现和终点控制的数值实验，结果表明：基于粗糙集方法的转炉炼钢知识发现模型可以实现知识发现属性的有效约简，同时，采用最小规则支持度和信任度的规则提取算法，可以发现数据中隐藏的知识规则，实现转炉炼钢知识的自动获取；在转炉炼钢知识发现过程中，随着训练数据集的增大，提取出来的知识规则数目相应增多，但知识规则预测的命中率并不一定提高，且随着训练数据集的增大，系统的运算效率会降低，因此，训练集的数据量大小和训练集的代表性对粗糙集转炉炼钢知识发现有着重要的影响；粗糙集转炉炼钢知识发现模型随着规则支持度和信任度的增加，知识规则预测的精确性也越高，发现的有效知识规则数量会降低，但知识的覆盖面会应知识条件的约束范围狭小而显著降低，因此，应在实验的基础上选取较为合理的参数值，不能一味的追求较大的规则支持度和信任度；粗糙集-神经网络模型的输入层结点属性是由基于粗糙集模型确定的对转炉冶炼终点钢水的碳含量和温度有重要影响的因素作为终点预测模型输入参数，因此，相对于常规转炉神经网络终点预测模型，减少了输入层和隐含层的的结点数目，增加了模型网络结构表达的针对性，有效提高模型的计算效率和计算准确性。
因此，本文是针对复杂转炉炼钢过程知识发现与终点控制难题，引入粗糙集理论方法，建立基于粗糙集的转炉炼钢知识发现模型，以及粗糙集-神经网络模型终点预测模型；并以面向对象方法开发了相应的模型系统；以具体炼钢转炉生产过程数据进行了方法的验证及应用测试，表明了方法及系统的有效性。研究成果为转炉炼钢知识发现、终点控制优化等问题研究和生产控制提供了新方法和新手段。
BOF steelmaking is a complicated, multi-component, multi-phase and hightemperature physiochemical process with fast chemical reaction rate and manyinfluencing factors. The control core of the process is to control the endpointtemperature and carbon content of molten steel accurately. During the BOF steelmakingprocess, improving the accuracy of the endpoint control can reduce the tap-to-tap time,prolong the life of furnace lining, reduce the consumption of steel material, improve andstabilize the steel quality, reduce production costs and improve the BOF productivitysignificantly. Thereby, it is an important way to increase the competitiveness ofsteelmaking enterprises.
For now, the endpoint control of BOF steelmaking seriously relies on the engineersand site operators’ experiential knowledge in the majority of domestic steelmakingplants. And the experiential knowledge is mainly acquired by summarizing theexperiences and statistically analyzing the operational data simply. Due to the unevenqualities of the situ technicians and operators and the complexity of the workingconditions for actual steelmaking, the stability and accuracy of the endpoint control byhuman experience and simple statistical analysis can not meet the productionrequirements. Currently, the knowledge discovery based on artificial intelligence hasbeen widely used in various areas, and has got very obviously good results in practicalapplication. However, this research is still in its infancy in the field of BOF steelmaking.The production process of BOF steelmaking which has a complex smelting mechanismis influenced by many factors. The data collected in the smelting process ismultivariable, nonlinear and much high noisy. Therefore, to explore a discoveringmethod which can adapt to the complex characteristics of BOF steelmaking process anddiscover the converter steelmaking production knowledge and setup a system model forknowledge discovering and endpoint controlling have an important significance intheory and application.
For the characteristics of BOF steelmaking knowledge discovery and endpointcontrol, a BOF steelmaking knowledge discovery model and a rough set-neuralnetwork endpoint control model are established based on the rough set theory andneural network analysis. Using the proposed models, the BOF steelmaking productionknowledge can be acquired automatically and the BOF endpoint control method can be optimized. For the rough set-based BOF steelmaking knowledge discovery model, theproduction data can be preprocessed by cleaning, standardizing and straggling. Theimportant influencing factors of BOF steelmaking are served as the knowledgediscovery condition attribute and the molten steel carbon content and molten steeltemperature of BOF smelting endpoint are served as the knowledge discovery decisionattribute. Combined the association rules extract algorithm, the rough set theory methodis used to realize the BOF steelmaking knowledge discovery attribute reduction. TheBOF endpoint control model based on rough set-neural network combined withmethodological characteristics of rough set theory and neural network theory. Theminimum condition attribute set determined by rough set theory method is served as theinput of the neural network conditions and has a major impact on the decision attributeset. The model can effectively simplify the network structure and improve theadaptability, accuracy and computational efficiency of the neural network model. Then,using object-oriented graphical modeling technology, visualization technology and theoptional Microsoft's Visual Basic6.0programming technology, a BOF steelmakingknowledge discovery and endpoint control system model is developed. It is much moreadaptable, flexible and reliable.
The numerical experiments for knowledge discovery and endpoint control areperformed based on the Xinyu210t BOF steelmaking plant production process and datainformation. The results show that: BOF steelmaking knowledge discovery model basedon rough set method could achieve effective reduction of knowledge discoveryproperties. At the same time, the rule extraction algorithm which uses the minimum rulesupport and confidence can find knowledge rules hidden in the data and achieve theautomatic acquisition of BOF steelmaking knowledge. In BOF steelmaking knowledgediscovery process, with the increase of training data set, the number of knowledge rulesextracted increases correspondingly. However, the hit rate predicted by the knowledgerules does not necessarily improve and the operational efficiency of the system willreduce. Therefore, the data size of the training set and the representativeness of thetraining data have important impact on the rough set BOF steelmaking knowledgediscovery. With the increase of rule support and confidence, the predictive accuracy ofthe model knowledge rules become higher and the number of effective knowledge ruleswill reduce, but the coverage of knowledge should be significantly reduced withconstraint range narrow of knowledge conditions. Therefore, more reasonable parametervalues should be selected based on experiments and we should not just pursue of the larger rules support and trust. The input layer node propertie of rough set-nervenetwork model is that the input parameters of the end point prediction model aredetermined by analyzing the factors which have major impact on the endpoint of thesmelting steel endpoint of the carbon content and the temperature of molten steel basedon rough set model. Therefore, related to the conventional BOF neural networkendpoint prediction model, the number of nodes of input layer and hidden layer isreduced and the pertinence of the model network structure expression is increased. Also,the computational efficiency and accuracy of the model is improved effectively.
Aiming at the complex BOF steelmaking process knowledge and endpoint controlproblem, the BOF steelmaking knowledge discovery model based on rough set and therough set-neural network model endpoint prediction model are established throughintroducing the rough set theory in this paper. And, model system based onobject-oriented method is developed. Method validation and practical application whichindicate the effectiveness of method and system are achieved by analyzing the specificBOF steelmaking production process data. Research results provide new methods andmeans for the BOF steelmaking knowledge discovery, end control optimization andproduction control.
引文
[1]王承宽,王勇,李中金.我国转炉炼钢技术的发展[J].炼钢.2002,18(5):55-57.
[2]张瑞祥.顶吹氧气转炉静态动态控制及其发展趋势[C].第五届转炉炼钢学术会议论文集.1998.8:28-31.
[3]刘浏.转炉全自动吹炼技术[J].冶金自动化.1999,4:1-6.
[4]胡燕,何腊梅.数据挖掘技术在转炉终点控制中的应用[J].钢铁技术.2010,(5):39-42.
[5]王雅贞,张岩,张红文编.氧气顶吹转炉炼钢工艺与设备[M].北京:冶金工业出版社,2001.
[6]施月循,邢玉禄,王寿同等编.钢铁冶金工艺学[M].沈阳:东北大学出版社,1996.
[7]冯杰,张红文.转炉炼钢生产[M].北京.冶金工业出版社.2006:74-1147.
[8]闫博.转炉炼钢智能控制方法的研究[D].东北大学硕士论文,2005,1.
[9](苏)B-N·巴普基兹曼斯基著.曹兆民译.氧气转炉炼钢过程理论[M].上海:上海科学技术出版社,1979.
[10] Mehmed Kantardzic.数据挖掘—概念、模型、方法和算法[M].北京:清华大学出版社，2003,15-23.
[11]曹存根.面向专家的知识获取[M].北京:科学出版社,1997.
[12]范宇中.智能信息系统中的知识获取研究[D].武汉科技大学硕士论文,2004,1.
[13]李剑锋,李一军,祁威等.数据挖掘在公司财务分析中的应用[J].计算机工程与应用.2005，(2):217-219.
[14]冯建生.KDD及其应用[J].宝钢技术.1999(3).27-31.
[15] Fayyad U, Piatetsky-Shapiro G, Smyth P. Knowledge Discovery and Data Mining: Towards aunifying Framework[J]. Proc of KDD-96. Menlo Park, CA:AAAI Press,1996,82-88.
[16]崔庆安.工业系统集成信息处理技术及其应用研究[D].西安科技大学硕士论文,2004.4.
[17]史忠植.知识发现[M].北京:清华大学出版社.2002:8-9.
[18]谢灵杰.高炉铁水硅含量预测中的直接经验和间接经验[D].重庆大学硕士论文.2003,5.
[19] Martin Trevor,Majidian Andrei. Finding fuzzy concepts for creative knowledge discovery[J].International Journal of Intelligent Systems.2013,28(1):93-114.
[20] Tomanová, Iva, Kupka Jirí.Implementation of background knowledge and properties inducedby fuzzy confirmation measures in apriori algorithm[J]. Advances in Intelligent Systems andComputing.2012,189:533-542.
[21] Pedrycz Witold, Song Mingli.Granular fuzzy models: A study in knowledge management infuzzy modeling[J].International Journal of Approximate Reasoning.2012,53(7):1061-1079.
[22]邱卫根.基于粗集的模糊属性值信息系统的知识获取[J].计算机工程与应用.2006,20:138-140.
[23]孙晋众,陈世权.一种基于模糊集值统计的集对预测方法[J].模糊系统与数学.2009,23(3):56-60.
[24]王基一,顾沈明.一种基于模糊粗糙集知识获取方法[J].计算机科学,2004,31(6):169-170.
[25]巫兆聪.粗糙集理论在遥感影像分类中的应用[D].武汉大学博士论文.2004,11
[26] Duenyas Shahaf, Margaliot Michael. Knowledge extraction from a class of support vectormachines using the fuzzy all-permutations rule-base. IEEE SSCI2011-Symposium Series onComputational Intelligence.2011,59-65.
[27] Arun Kumar M.,Khemchandani Reshma,Gopal, M.ect. Knowledge based Least Squares Twinsupport vector machines[J]. Information Sciences.2010,180(23):4606-4618.
[28]胡迎春,李尚平.基于支持向量机的优化知识库系统设计研究[J].计算机工程与设计.2007,28(14):3455-3457.
[29] Khemchandani Reshma,Jayadeva,Chandra Suresh.Knowledge based proximal support vectormachines[J]. European Journal of Operational Research.2009,195(3):914-923.
[30]魏玲,祁建军,张文修.基于支持向量机的决策系统知识发现[J].西安交通大学学报.2003,37(10):995-998.
[31]许建华,张学工,李衍达.支持向量机的新发展[J].控制与决策,2004,19(5):481-484.
[32] Barakat Nahla,Bradley Andrew P.The effect of domain knowledge on rule extraction fromsupport vector machines[J]. Lecture Notes in Computer Science.2009,5632:311-321.
[33] Le Quoc V., Smola Alex J.,G rtner Thomas.Simpler knowledge-based support vectormachines[C]. ACM International Conference Proceeding Series.2006,148:521-528.
[34]王志海,胡可云,胡学钢等.基于粗糙集合理论的知识发现综述[J].模式识别与人工智能.1998,11(2):176-183.
[35] Pawlak Z. Rough Set-Theoretical Aspect of Reasoning about Data[M].Dordrecht, Boston,London: Kluwer Academic Publishers,1991.
[36]陈丽芳,朱晓亮,付景红.粗糙集在熟料强度影响因素选取中的应用研究[J].计算机应用与软件.2008,25(11):107-108
[37]常晓艳,刘振娟.基于粗糙集属性约简的过程控制规则提取[J].仪器仪表学报.2004,(4):881-883.
[38] Nguyen, Tuan Trung.Rough set approach to domain knowledge approximation[J].Fundamenta Informaticae.2004,59(2-3):261-270.
[39] Ramanna Sheela, Peters James F., Ahn Taechon.Software quality knowledge discovery: Arough set approach.Proceedings-IEEE Computer Society's International Computer Softwareand Applications Conference.2002,1140-1145.
[40] Peters J.F.,Skowron A..A rough set approach to knowledge discovery[J].International Journalof Intelligent Systems,.2002,17(2):109-112.
[41]苗夺谦.Rough Set理论中连续属性的离散化方法[J].自动化学报.2001,27(3):296-302.
[42] Pawlak Z. Knowledge and uncertainty a rough set approach[J]. Springer-Verlag New YorkInc.1993,34.
[43] Banerjee Mohua, Mitra Sushmita, Pal Sankar K.Knowledge-based fuzzy MLP with roughsets[C]. IEEE International Conference on Neural Networks-Conference Proceedings.1997,1:499-504.
[44] Lambert-Torres Germano,Quintana Victor Hugo, da Silva Alexandre P.Alvesetc.Knowledge-base reduction based on rough set techniques[J]. Canadian Conference onElectrical and Computer Engineering.1996,1:278-281.
[45]刘建成,蒋新华,吴今培.一种知识推理规则归纳系统的实现[J].系统工程.2003,21(3):107-112
[46]石倩,陈荣,鲁明羽.基于规则归纳的信息抽取系统实现[J].计算机工程与应用.2008,44(21）：166-170.
[47] Quinlan J R. Induction of decision trees[J]. Machine Learning,1986,(1):81-106.
[48] Soderlan S.Learning information extraction rules for semi-struc-tured and freetext[J].Machine Learning,1999,34(1-3):233-272.
[49] Hsu C-N, Dung M-T.Generating finite-state transducers for semi-structured data extractionfrom the Web[J].Information Systems,1998,23(8):521-538.
[50] Hidanand Apte, Sholom Weiss. Data mining with decision trees and decision rules[J]. Futuregeneration computer systems.1997,13.197-210.
[51]刘同明.数据挖掘技术及其应用[M].长沙.国防工业出版社,2001.
[52]沈学利,钟华.决策树与数据仓库结合的研究与应用[J].计算机工程.2011,37(11):89-91.
[53]邹媛.基于决策树的数据挖掘算法的应用与研究[J].科学技术与工程.2010,10(18):4510-4515.
[54]杨静,张楠男,李建等.决策树算法的研究与应用[J].计算机技术与发展.2010,20(2):114-116.
[55] Kwon, ByungO.2003. Metaweb service-Buildingweb based open decision support systembased on web services[J], Expert Systemswith Applications,24(4):375-389.
[56]冯文江,刘震,秦春玲.案例推理在认知引擎中的应用[J].模式识别与人工智能.2011,24(3):400-404.
[57] Lee J K,Kim M Y.Case-based learning for knowledge-based optimization modelingsystems:UNIK-case[J].Expert Systems with Application.1993,(6):87-95.
[58]杨先奇,李建洋,兰添才等.案例推理技术及其在决策科学中的应用研究[J].东华理工大学学报(自然科学版).2008,31(2):187-191.
[59]王东,刘怀亮,徐国华.案例推理在故障诊断系统中的应用[J].计算机工程.2003,29(12):10-12.
[60]刘胜荣.空气质量评价智能信息处理技术研究[D].西安建筑科技大学硕士论文.2007,5.
[61]李芸.基于贝叶斯信念网络的数据分类挖掘算法[J].计算机科学.2006,33(10):157-158.
[62]李明,刘鲁,苗蕊等.基于贝叶斯信念网络的多案例库检索方法[J].北京工业大学学报.2012,38(1):81-85.
[63] Boughanem M,Brini A, Dubois D.Possibilistic networks for informationretrieval[J].International Journal of Approximate Reasoning.2009,50(7):957-968．
[64] Holland J H. Adaptation in natural and artificial System[J]. Ann Arbor: University ofMichigan Press,1975.
[65]张琳.基于GA-BP混合算法的转炉终点优化控制模型[D].重庆大学硕士论文.2004,5.
[66]张雪江,朱向阳,钟秉林等.基于退火演化算法的知识获取机制的研究[J].控制理论与应用.1998,15(1):93-99.
[67] Matwin S. Szapiro T，Haigh K. Genetic algorithms approach to a negotiation supportsystem[C]. IEEE Trans on System. Man and Cybernetics.1991,21(1):102-114.
[68]史忠植.神经网络[M].2009.北京:高等教育出版社,2009.
[69] Towell G G, Shavlik J W. Knowledge based artificial neural networks[J]. ArtificialIntelligence.1994,70(1/2):119-165.
[70] Towell G G, Shavlik J M. Extracting refined rules from knowledge based neural networks[J].Mach Learn.1993,13(1):71-101.
[71]刘振凯,贵忠华,蔡青.基于神经网络结构学习的知识求精方法[J].计算机研究与发展.1999,36(10):1169-1173.
[72]常伟,刘文剑,许之伟等.基于人工神经网络的工艺知识表示方法的研究[J].哈尔滨工业大学学报.2000,32(3):132-136.
[73]钱大群,孙振飞.神经网络的知识获取与行为解释[J].自动化学报.1994,20(3):348-351.
[74]张健沛,王爱华,魏永明等.人工神经网络用于知识获取[J].哈尔滨工业大学学报.1999,20(6):42-46.
[75]栗然,赵敏,徐荣根等.通用可视化网络建模的知识推理[J].电力自动化设备.2002,22(9):38-40.
[76]杨琳珊,齐德昱.基于知识的可视化产品概念设计系统的实现[J].华南理工大学学报(自然科学版).1999,27(8):37-40.
[77]王勇军,徐明,胡守仁.面向对象知识库系统CAOBS/V1.2的可视化查询子系统[J].计算机研究与发展.1998,35(8):684-688.
[78]袁守谦,邢曼华,李都宏等.转炉冶炼专家系统开发研究[J].西安建筑科技大学学报（自然科学版）.2012,44(1):137-140.
[79]谢书明,陈昌,丁惜瀛.基于BP神经网络的转炉炼钢终点预报[J].沈阳工业大学学报.2007,29(6):707-710.
[80]韩敏,张俊杰,赵耀等.基于模糊加权的转炉炼钢磷分配比计算模型[J].冶金自动化.2010,34(3):14-18.
[81]蔡煜东,程兆年,陈念贻等.遗传程序设计用于工业调优——炼钢转炉炉龄预测[J].自动化学报.1997,23(1):50-56.
[82]张辉宜,周奇龙,袁志祥等.样本自选择回归分析算法在转炉炼钢中的应用[J].钢铁研究学报.2011,23(12):5-8.
[83]陈家祥.钢铁冶金学(炼钢部分)[M].北京:冶金工业出版社,1999.
[84]顾宏.转炉过程模型与控制技术[J].江苏冶金.2003,31(4):8-10.
[85] Ken-Iwamura，Macao FurusawaMasakazu Miyamoto. New endpoint control system withauto-parameter-turning in BOF[C].Steelmaking Conference Proceedings.1995:715-719.
[86] D.Anderson, C.M.Barnes, H.J.Whittaker. Fully dynamic process control of the BOS in BritishSteel[C].Steelmaking Conference Proceedings.1991:379-387.
[87] Teruki Makino，Shigeru Omiya, Nobukazu Kitagawa. Automatic operation of converters atmizushima works[C].Steelmaking Conference Proceedings.1989:67-71.
[88] Hiroshi Yamane, Michitaka Kanemoto,Tooru Yoshida. Development of expert system andonline sensor for BOF process[C].Steelmaking Conference Proceedings.1991:453-458.
[89]周子懿,将慎言. LD转炉动态控制CRM模型[J].冶金自动化:1989,13(2),3-8.
[90]史战东.转炉终点控制模型的比较分析和改进研究[D].重庆大学硕士论文,2008,6.
[91]雷新泉,雷曼.转炉炼钢静态模型的初步探讨[J].钢铁研究,1994(2):8-12.
[92]黄今侠.转炉炼钢终点静态控制预测模型[D].天津大学硕士论文,2005,6.
[93]胡燕,何腊梅.转炉炼钢终点控制模型的方法研究[J].钢铁技术.2009,(6):14-16.
[94]刘浏.转炉全自动吹炼技术[J].冶金自动化.1999,4:1-6.
[95]代友训.转炉炼钢终点准动态控制系统[D].重庆大学硕士论文,2007,4.
[96]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.
[97]谢书明,陶钧,柴天佑.基于神经网络的转炉炼钢终点控制[J].控制理论与应用.2003，20(6):903-907.
[98] Akcayol, M. Ali, Cinar, Can. Artificial neural network based modeling of heated catalyticconverter performance[J]. Applied Thermal Engineering.2005,25:2341-2350.
[99]杨立红,刘浏,何平.基于自适应模糊神经网络系统的转炉终点磷的预报控制模型[J].钢铁研究学报.2002,14(4):47-51.
[100]田民乐,刘少民.基于模糊神经网络的炼钢炉静态建模[J].北京科技大学学报.1998,20(2)：136-139.
[101] Abbas, Ghulam,Farooq, Umar; Asad, Muhammad Usman.Application of neural networkbased model predictive controller to power switching converters[C].Proceedings of the2011International Conference and Workshop on the Current Trends in InformationTechnology,.2011,132-136.
[102] Yang, Lihong,Liu, Liu; He, Ping. Control of carbon content and temperature at end point forconverter process based on2-output neural network[J]. Kang T'ieh/Iron and Steel(Peking).2002,37(11):13-15.
[103] Wang Jianhui,Xu, Lin; Fang, Xiaoke ect.Class of GA-RBF neural network control for theBOF steelmaking static model[J].Journal of Southeast University (Natural ScienceEdition).2005,35(SUPPL):90-94.
[104] K Hornik K, M Stinchcombe H White.Multilayer feed forward network are universalapproximators[J]. Neural Networks,1989,(2):359-366.
[105]王小平,曹立明.遗传算法理论、应用与软件实现[M].西安:西安交通大学出版社,2002.(1):73-78.
[106]刘杰,王媛.一种高效混合遗传算法[J].河海大学学报.2002,30(2):49-53.
[107]郭彤城,慕春棣.并行遗传算法的新进展[J].系统工程理论与实践,2002,(2):15-21..
[108]侯格贤,吴成柯.遗传算法的性能分析[J].控制与决策.1999,14(3):257-260.
[109] Díaz-Cruz M, Morales, R.D.,Olivares etc.Physical and mathematical models of gas-liquiddynamics in BOF converters[C]. Steelmaking Conference Proceedings,.2002,85:737-748.
[110] Yuhendri, Muldi, Ashari, Mochammad; Purnomo, M.H.Linear Quadratic Regulator designfor modular matrix converter using Genetic Algorithm[C].2011IEEE3rd InternationalConference on Communication Software and Networks.2011,175-179.
[111]樊莉萍,王成钢,张建伟等.转炉吹炼实时控制专家系统RESC的设计与实现[J].计算机研究与发展.1997,34(6):432-438.
[112]陶钧,柴天佑,李小平等.转炉炼钢智能控制方法及应用[J].控制理论与应用.2001.18(S1):129-133.
[113]襄祖安.转炉炼钢造渣操作指导专家系统[J].上海金属.13(5):45-49.
[114]樊俊飞,李永和,许春雷等.宝钢转炉吹炼控制模拟在线专家系统[J].北京科技大学学报.1995,17(S1):6-11.
[115] Hofinger, Stephan Hubmer,Rudolf etc. Steel expert takes command optimized performance onBOF converter[J]. AISTech2012Iron and Steel Technology Conference andExposition.2012,925-935.
[116]袁守谦,邢曼华,李都宏等.转炉冶炼专家系统开发研究[J].西安建筑科技大学学报（自然科学版）2012.44(1):137-140.
[117]周双喜.一种用于转炉炉口微压差控制的混合控制策略[J].自动化与仪器仪表.2011,(6):14-16.
[118]于立业,徐林,王建辉等.基于声强的转炉氧枪枪位控制专家系统[J].冶金自动化.2005，(5):11-14.
[119] Deo Brahma, Balakrishnan V. Application of model predictive control in a dynamic system:An application to BOF steelmaking process[C]. AISTech2009-Proceedings of the Iron andSteel Technology Conference.2009,1:801-810.
[120] Ceriani Alfredo,Aprile Giovanni, ScipoloVittorio etc. Dynamic modeling of the BOF forendpoint prediction using EFSOP technology results and implementation at riva taranto[C].AISTech2010-Proceedings of the Iron and Steel Technology Conference.2010,997-1003.
[121] Huber J.-C,Lehmann J.,Cadet R. Comprehensive dynamic model for BOF process: A glimpseinto thermal efficiency mechanisms[J].Revue de Metallurgie.2008,105(3):121-126.
[122] Graveland-Gisolf E., Mink P.,Overbosch A etc. Slag-droplet model: A dynamic tool tosimulate and optimise the refining conditions in BOF[J]. Steel Research.2003,74(3):125-130.
[123]史成钢.转炉控制动态校正模型的分析与改进[J]鞍钢技术.1992,(5):36-41.
[124] Kuo-Chih CHOU,Uday B.PAL,Ramana G.REDDY.A general model for BOP decarburization[J].ISLJ international.1993.33(8):862-867.
[125]李彦平,潘德惠.BOF系统的炉气分析及其自动控制[J].控制与决策.1988,(2):7-10.
[126]张润宇,肖兵,张文弟.转炉钢水碳含量估计[J].自动化学报.1993,19(3):18-20.
[127] S.Y.Yun, K.S.Chang, S.M.Byun. Dynamic prediction using neural network for automation ofBOF process in steel industry[J].I&SM.1996,8:37-42.
[128]干勇.炼钢—连铸新技术800问[M].北京:冶金工业出版社.2003,6-7.
[129]沈昶,施雄梁,汤曙光等.烟气分析动态控制炼钢在马钢的应用[C].2005中国钢铁年会论文集,162–165.
[130] Robertson K.J., Balajee S.R.,Shearer, J.M. etc. Sublance dynamic control operation and itseffect on the performance of the Inland Steel Company's No.4BOF shop[J]. I&SM.1989,16(8):36-42.
[131] Takemura Yozo,Fukuda Shigemi,Saito Toyokazu etc. BOF dynacmic control using sublancesystem[J]. Nippon Steel Technical Report.1978,(11):57-68.
[132] Spanjers M.,Glitscher W. Sublance-based on-line slag control in BOF steelmaking[J].AISTech2005-Iron and Steel Technology Conference Proceedings.2005,1:723-728.
[133] Friedl Erich,Kaiser Heinz Peter. Automatic blowing process in BOF and direct tapping usingthe sublance system[J]. MPT. Metallurgical plant and technology.1990,13(1):28-32.
[134]吴健鹏,刘先同,何金平等.150t转炉副枪及自动炼钢系统的应用[J].武钢技术.2011,49(3):13-18.
[135]王忠刚,任科社,刘忠建.副枪技术在莱钢120t转炉上的应用[J].中国冶金.2009,19(11):30-32.
[136] Gruner, H., Wiemer, H.-E., Fix, W. etc. New metallurgical insight into BOF steelmaking andimproved process control using sublance techniques and bottom gas stirring[J]. I&SM.1985,12(3):31-36.
[137] Nashiwa H.,Mizuno T., Ohi J. etc. Effective use of returned LD slag and dolomite andoperation with sublance system[J].Ironmaking and Steelmaking.1978,5(3):95-102.
[138]左康林,邹俊苏,孙晓辉等.转炉副枪测量与成分预报技术[J].炼钢.2009,25(2):59-61.
[139]陈忠清,黄林湘.HFS系列转炉副枪测头研制与应用[J].计量装置及应用.2005,15(3):23-25.
[140]陈重丽,张妙法,陈业泰等.转炉副枪用测铁水液面探头的研制[J].宝钢技术.1989,(3):33-34.
[141]王胜.BOF副枪控制和数据处理.冶金自动化[J].2006,(4):29-33.
[142]章文超.转炉副枪系统型式与国产化[J].世界钢铁.2010,(2):23-26.
[143]汪大洲.国外转炉副枪及其探头[J].冶金自动化.1977,(3):110-117.
[144] Romanovskii Oleg A.,Matvienko Gennadii G.,Kharchenko Olga V. etc. The use of frequencyconverter of femtosecond laser radiation in broadband lidar gas analysis of atmosphere[J].Proceedings of SPIE-The International Society for Optical Engineering.2006,6522-6524.
[145] Niebuhr, M., Gabriel, A.,Koch, M.H.J..Analysis of fluorescence effects in a position-sensitivegas detector using a time-stamp time-to-digital converter[J]. Nuclear Instruments andMethods in Physics Research.2003,510(3):309-317.
[146] Mabuchi Masaki,Kokubu Haruo,Nakato Hakaru etc. Numerical analysis of the gas flow andcombustion reaction in converter[J].Journal of the Iron and Steel Institute ofJapan.1989,75(7):1139-1145.
[147]刘文,杨宪礼,白彦.转炉采用炉气分析法进行动态控制[J].炼钢.2003,19(5):48-51.
[148]万雪峰,张贵玉,林东等.转炉炉气成分变化规律的初步研究[J].中国冶金.2006,16(1):23-26.
[149]胡志刚,何平,刘浏等.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.
[150]袁建路,董中奇,黄伟青等.对转炉炉气在线检测的数学模拟分析[J].物理测试.2012,31(1):13-16.
[151]丁长江,刘国平,周俐.利用炉气CO浓度曲线监控转炉造渣操作[J].中国冶金.2007,17(10):16-19.
[152] Díaz-Cruz M,Morales R.D,Olivares etc.Physical and mathematical models of gas-liquiddynamics in BOF converters[C].2002Proceedings-Ironmaking Conference.2002,825-836.
[153] O'Shaughnessy Earl J.,Bicknese Eugene H. Improved BOF practice through waste gssanalysis[C]. Proceedings-National Open Hearth and Basic Oxygen SteelConference.1974,5:169-177.
[154]石知机,汪国才,李应江.炉气分析终点控制技术在马钢转炉的应用[J].钢铁.2007,42(4):24-26.
[155]张贵玉,万雪峰,林东等.转炉炉气分析动态控制技术的应用[J].钢铁.2007,42(9):29-32.
[156] Iso, Hei-ichiro, Jyono, Yutaka etc. Dynmic refining control by analysis of exhaust gas fromLD converter[J].Transactions of the Iron and Steel Institute of Japan.1987,27(5):351-359.
[157] Takawa Takeshi,Katayama Katsumi,Katohgi Ken etc. Analysis of converter process variablesfrom exhaust gas[J]. Transactions of the Iron and Steel Institute of Japan.1988,28(1):59-67.
[158]胡志刚,刘浏.炉气分析在转炉动态控制中的应用[J].钢铁研究学报.2002,13(3):68-73.
[159] Suraj, Zbigniew. Discovery of concurrent data models from experimental tables: a rough setapproach. Fundamenta Informaticae.1996,28(3):353-376.
[160] Grzymala-Busse J W. LERS: A System of Knowledge Discovery Based on Rough Sets[C].Proc of5th Int Workshop RSFD’96.Tokyo,1996,443-444.
[161]樊俊飞,李永如,姚海石.宝钢转炉吹炼控制模拟在线专家系统[J].宝钢技术.1996，4：50-54
[162]任卫国.基于粗糙集理论的机器人视觉跟踪系统研究[D].河北工业大学,2007.
[163] Ramanna Sheela, Peters James F., Ahn Taechon.Software quality knowledge discovery: Arough set approach[C].Proceedings-IEEE Computer Society's International ComputerSoftware and Applications Conference.2002,1140-1145.
[164] Nguyen, Tuan Trung.Rough set approach to domain knowledge approximation[J].Fundamenta Informaticae.2004,59(2-3):261-270.
[165]张文修,吴伟志,梁吉业.粗糙集理论与方法[M].北京:科学出版社,2001.
[166]张勇.粗糙集-神经网络智能系统在浮选过程中的应用[D].大连理工大学博士学位论文,2006.
[167]赵卫东,陈国华.粗集与神经网络的集成技术研究[J].系统工程与电子技术.2002,24（10）：103-107.
[168] J. Ilona, M. Chris, W. Tim.An investigation into the application of neural networks, fuzzylogic, genetic algorithms, and rough sets to automated knowledge acquisition forclassification problems[J]. Neurocomputing.1999,24(1-3):37-54.
[169]陈遵德. Rough Set神经网络智能系统及其应用[J].模式识别与人工智能.1999,12(1):1-5.
[170] Ahn B.S，Cho S. S，Kim C. Y..The integrated methodology of rough set theory and artificialneural network for business failure prediction[J].Expert system withApplication.2000,18:65-74.
[171] Szcauka M.S. Rough set methods for constructing artificial neural networks[J]. Americansociety of mechanical engineers.1996,79(7):9-14.
[172] Hashei R. R，LeBlance L. A，etl. Hybired intelligent system for predicting bank holdingstructure[J]. European Journal of Operational Research,1999,109(2):390-402.
[173]胡寿松,何亚群.粗糙决策理论与应用[M].北京:北京航空航天大学出版社,2006.
[174] Pawlak Z. Rough sets[J]. lnt. J. of information and computer science.1982,11:341-356.
[175]王钰,苗夺谦.关于Rouge Set理论与应用的综述[J].模式识别与人工智能.1996,9(4):337-344
[176]刘清,黄兆华,姚力文.Rough集理论:现状与前景[J].计算机科学.1997,24(4):1-5.
[177]韩祯祥,张琦,文福栓.粗糙集理论及其应用综述[J].控制理论与应用.1999,16(2):153-157.
[178]潘丹.基于粗糙集理论的混合智能知识处理研究[D].华南理工大学博士学位论文,2001.
[179] A. Roy,S. K. Pal.Fuzzy discretization of feature space for a rough set calssifier[J]. PatternRecognition Letters.2003,24(6):895-902.
[180] M. R. Chmielewski, J. W. Grzymala-Busse, et. al.The rule induction system LERs一Aversion for personal computer[J]. Found. Computer Decision Sci.1993.18(3-4):181-212.
[181]王国胤. Rough集理论与知识获取[M].西安交通大学出版社.2001.
[182] A. Roy，S. K. Pal. Fuzzy discretization of feature space for a rough set calssifier[J]. PatternRecognition Letters.2003,24(6):895-902
[183] M. R. Chmielewski, J. W. Grzymala-Busse. The rule induction system LERs一A version forpersonal computer[J].Found. Computer Decision Sci.1993.18(3-4):181-212.
[184]郭志懋,周傲英.数据质量和数据清洗研究综述[J].软件学报.2002,13(11):2076-2082.
[185]刘叶玲,朱艳伟.加权数据融合算法及其应用举例[J].西安科技大学学报.2005,25(2)：253-255.
[186]朱学锋,韩荣阁,杨若红.基于模糊预测系统的观测数据野值剔除方法[J].系统工程与电子技术.2006,28(3):478-482.
[187]李梦奇,白晓军,匡同春等.工程技术领域等精度数据异常值判定系统[J].计量技术.2006,3：57-59.
[188] Amitava R,Sankar K. P.Fizzy discretization of feature space for a rough set classifer.[J]Pattern Recognition Letters,200324:895-902.
[189]谢洪,程浩忠,牛东晓.基于信息嫡的粗糙集连续属性离散化算法[J].计算机学报.2005,28(9):1570-1574.
[190]刘胜军,杨学兵,蔡庆生.关系数据库中概念层次自动提取算法研究[J].计算机应用研究.1999,(12):15-17.
[191]曾黄麟.粗集理论及其应用[M].重庆:重庆大学出版社,1998.
[192]张文修,吴伟志.粗糙集理论介绍和研究综述[J].模糊系统与数学.2000.14(4):84-89.
[193]程岩,黄梯云.信息系统中一种面向粗糙集的数据挖掘方法[J].情报学报.2001,20(1),90-99.
[194]杨敏,沈春林.Matlab神经网络工具箱编程和Delphi对其调用[J].计算机工程，2001,27(11):92-94.
[195]田雨波.混合神经网络技术[M].北京:科学出版社.2009.
[196]丛爽.面相Matlab工具箱的神经网络理论与应用[M].北京:中国科学技术大学出版社.1998.
[197]杨建刚.人工神经网络实用教程[M].杭州:浙江大学出版社.2001.
[198]张磊,胡春,钱锋等．BP算法局部极小问题改进的研究进展[J].工业控制计算机.2004，17(9):33-50.
[199] K Hornik K, M Stinchcombe H White.Multilayer feed forward network are universalapproximators[J]. Neural Networks.1989,(2):359-366.
[200]冯明霞,李强,邹宗树.转炉终点预测模型中异常数据检验的研究[J].中国冶金.2006,16(9)：27-31.
[2]张瑞祥.顶吹氧气转炉静态动态控制及其发展趋势[C].第五届转炉炼钢学术会议论文集.1998.8:28-31.
[3]刘浏.转炉全自动吹炼技术[J].冶金自动化.1999,4:1-6.
[4]胡燕,何腊梅.数据挖掘技术在转炉终点控制中的应用[J].钢铁技术.2010,(5):39-42.
[5]王雅贞,张岩,张红文编.氧气顶吹转炉炼钢工艺与设备[M].北京:冶金工业出版社,2001.
[6]施月循,邢玉禄,王寿同等编.钢铁冶金工艺学[M].沈阳:东北大学出版社,1996.
[7]冯杰,张红文.转炉炼钢生产[M].北京.冶金工业出版社.2006:74-1147.
[8]闫博.转炉炼钢智能控制方法的研究[D].东北大学硕士论文,2005,1.
[9](苏)B-N·巴普基兹曼斯基著.曹兆民译.氧气转炉炼钢过程理论[M].上海:上海科学技术出版社,1979.
[10] Mehmed Kantardzic.数据挖掘—概念、模型、方法和算法[M].北京:清华大学出版社，2003,15-23.
[11]曹存根.面向专家的知识获取[M].北京:科学出版社,1997.
[12]范宇中.智能信息系统中的知识获取研究[D].武汉科技大学硕士论文,2004,1.
[13]李剑锋,李一军,祁威等.数据挖掘在公司财务分析中的应用[J].计算机工程与应用.2005，(2):217-219.
[14]冯建生.KDD及其应用[J].宝钢技术.1999(3).27-31.
[15] Fayyad U, Piatetsky-Shapiro G, Smyth P. Knowledge Discovery and Data Mining: Towards aunifying Framework[J]. Proc of KDD-96. Menlo Park, CA:AAAI Press,1996,82-88.
[16]崔庆安.工业系统集成信息处理技术及其应用研究[D].西安科技大学硕士论文,2004.4.
[17]史忠植.知识发现[M].北京:清华大学出版社.2002:8-9.
[18]谢灵杰.高炉铁水硅含量预测中的直接经验和间接经验[D].重庆大学硕士论文.2003,5.
[19] Martin Trevor,Majidian Andrei. Finding fuzzy concepts for creative knowledge discovery[J].International Journal of Intelligent Systems.2013,28(1):93-114.
[20] Tomanová, Iva, Kupka Jirí.Implementation of background knowledge and properties inducedby fuzzy confirmation measures in apriori algorithm[J]. Advances in Intelligent Systems andComputing.2012,189:533-542.
[21] Pedrycz Witold, Song Mingli.Granular fuzzy models: A study in knowledge management infuzzy modeling[J].International Journal of Approximate Reasoning.2012,53(7):1061-1079.
[22]邱卫根.基于粗集的模糊属性值信息系统的知识获取[J].计算机工程与应用.2006,20:138-140.
[23]孙晋众,陈世权.一种基于模糊集值统计的集对预测方法[J].模糊系统与数学.2009,23(3):56-60.
[24]王基一,顾沈明.一种基于模糊粗糙集知识获取方法[J].计算机科学,2004,31(6):169-170.
[25]巫兆聪.粗糙集理论在遥感影像分类中的应用[D].武汉大学博士论文.2004,11
[26] Duenyas Shahaf, Margaliot Michael. Knowledge extraction from a class of support vectormachines using the fuzzy all-permutations rule-base. IEEE SSCI2011-Symposium Series onComputational Intelligence.2011,59-65.
[27] Arun Kumar M.,Khemchandani Reshma,Gopal, M.ect. Knowledge based Least Squares Twinsupport vector machines[J]. Information Sciences.2010,180(23):4606-4618.
[28]胡迎春,李尚平.基于支持向量机的优化知识库系统设计研究[J].计算机工程与设计.2007,28(14):3455-3457.
[29] Khemchandani Reshma,Jayadeva,Chandra Suresh.Knowledge based proximal support vectormachines[J]. European Journal of Operational Research.2009,195(3):914-923.
[30]魏玲,祁建军,张文修.基于支持向量机的决策系统知识发现[J].西安交通大学学报.2003,37(10):995-998.
[31]许建华,张学工,李衍达.支持向量机的新发展[J].控制与决策,2004,19(5):481-484.
[32] Barakat Nahla,Bradley Andrew P.The effect of domain knowledge on rule extraction fromsupport vector machines[J]. Lecture Notes in Computer Science.2009,5632:311-321.
[33] Le Quoc V., Smola Alex J.,G rtner Thomas.Simpler knowledge-based support vectormachines[C]. ACM International Conference Proceeding Series.2006,148:521-528.
[34]王志海,胡可云,胡学钢等.基于粗糙集合理论的知识发现综述[J].模式识别与人工智能.1998,11(2):176-183.
[35] Pawlak Z. Rough Set-Theoretical Aspect of Reasoning about Data[M].Dordrecht, Boston,London: Kluwer Academic Publishers,1991.
[36]陈丽芳,朱晓亮,付景红.粗糙集在熟料强度影响因素选取中的应用研究[J].计算机应用与软件.2008,25(11):107-108
[37]常晓艳,刘振娟.基于粗糙集属性约简的过程控制规则提取[J].仪器仪表学报.2004,(4):881-883.
[38] Nguyen, Tuan Trung.Rough set approach to domain knowledge approximation[J].Fundamenta Informaticae.2004,59(2-3):261-270.
[39] Ramanna Sheela, Peters James F., Ahn Taechon.Software quality knowledge discovery: Arough set approach.Proceedings-IEEE Computer Society's International Computer Softwareand Applications Conference.2002,1140-1145.
[40] Peters J.F.,Skowron A..A rough set approach to knowledge discovery[J].International Journalof Intelligent Systems,.2002,17(2):109-112.
[41]苗夺谦.Rough Set理论中连续属性的离散化方法[J].自动化学报.2001,27(3):296-302.
[42] Pawlak Z. Knowledge and uncertainty a rough set approach[J]. Springer-Verlag New YorkInc.1993,34.
[43] Banerjee Mohua, Mitra Sushmita, Pal Sankar K.Knowledge-based fuzzy MLP with roughsets[C]. IEEE International Conference on Neural Networks-Conference Proceedings.1997,1:499-504.
[44] Lambert-Torres Germano,Quintana Victor Hugo, da Silva Alexandre P.Alvesetc.Knowledge-base reduction based on rough set techniques[J]. Canadian Conference onElectrical and Computer Engineering.1996,1:278-281.
[45]刘建成,蒋新华,吴今培.一种知识推理规则归纳系统的实现[J].系统工程.2003,21(3):107-112
[46]石倩,陈荣,鲁明羽.基于规则归纳的信息抽取系统实现[J].计算机工程与应用.2008,44(21）：166-170.
[47] Quinlan J R. Induction of decision trees[J]. Machine Learning,1986,(1):81-106.
[48] Soderlan S.Learning information extraction rules for semi-struc-tured and freetext[J].Machine Learning,1999,34(1-3):233-272.
[49] Hsu C-N, Dung M-T.Generating finite-state transducers for semi-structured data extractionfrom the Web[J].Information Systems,1998,23(8):521-538.
[50] Hidanand Apte, Sholom Weiss. Data mining with decision trees and decision rules[J]. Futuregeneration computer systems.1997,13.197-210.
[51]刘同明.数据挖掘技术及其应用[M].长沙.国防工业出版社,2001.
[52]沈学利,钟华.决策树与数据仓库结合的研究与应用[J].计算机工程.2011,37(11):89-91.
[53]邹媛.基于决策树的数据挖掘算法的应用与研究[J].科学技术与工程.2010,10(18):4510-4515.
[54]杨静,张楠男,李建等.决策树算法的研究与应用[J].计算机技术与发展.2010,20(2):114-116.
[55] Kwon, ByungO.2003. Metaweb service-Buildingweb based open decision support systembased on web services[J], Expert Systemswith Applications,24(4):375-389.
[56]冯文江,刘震,秦春玲.案例推理在认知引擎中的应用[J].模式识别与人工智能.2011,24(3):400-404.
[57] Lee J K,Kim M Y.Case-based learning for knowledge-based optimization modelingsystems:UNIK-case[J].Expert Systems with Application.1993,(6):87-95.
[58]杨先奇,李建洋,兰添才等.案例推理技术及其在决策科学中的应用研究[J].东华理工大学学报(自然科学版).2008,31(2):187-191.
[59]王东,刘怀亮,徐国华.案例推理在故障诊断系统中的应用[J].计算机工程.2003,29(12):10-12.
[60]刘胜荣.空气质量评价智能信息处理技术研究[D].西安建筑科技大学硕士论文.2007,5.
[61]李芸.基于贝叶斯信念网络的数据分类挖掘算法[J].计算机科学.2006,33(10):157-158.
[62]李明,刘鲁,苗蕊等.基于贝叶斯信念网络的多案例库检索方法[J].北京工业大学学报.2012,38(1):81-85.
[63] Boughanem M,Brini A, Dubois D.Possibilistic networks for informationretrieval[J].International Journal of Approximate Reasoning.2009,50(7):957-968．
[64] Holland J H. Adaptation in natural and artificial System[J]. Ann Arbor: University ofMichigan Press,1975.
[65]张琳.基于GA-BP混合算法的转炉终点优化控制模型[D].重庆大学硕士论文.2004,5.
[66]张雪江,朱向阳,钟秉林等.基于退火演化算法的知识获取机制的研究[J].控制理论与应用.1998,15(1):93-99.
[67] Matwin S. Szapiro T，Haigh K. Genetic algorithms approach to a negotiation supportsystem[C]. IEEE Trans on System. Man and Cybernetics.1991,21(1):102-114.
[68]史忠植.神经网络[M].2009.北京:高等教育出版社,2009.
[69] Towell G G, Shavlik J W. Knowledge based artificial neural networks[J]. ArtificialIntelligence.1994,70(1/2):119-165.
[70] Towell G G, Shavlik J M. Extracting refined rules from knowledge based neural networks[J].Mach Learn.1993,13(1):71-101.
[71]刘振凯,贵忠华,蔡青.基于神经网络结构学习的知识求精方法[J].计算机研究与发展.1999,36(10):1169-1173.
[72]常伟,刘文剑,许之伟等.基于人工神经网络的工艺知识表示方法的研究[J].哈尔滨工业大学学报.2000,32(3):132-136.
[73]钱大群,孙振飞.神经网络的知识获取与行为解释[J].自动化学报.1994,20(3):348-351.
[74]张健沛,王爱华,魏永明等.人工神经网络用于知识获取[J].哈尔滨工业大学学报.1999,20(6):42-46.
[75]栗然,赵敏,徐荣根等.通用可视化网络建模的知识推理[J].电力自动化设备.2002,22(9):38-40.
[76]杨琳珊,齐德昱.基于知识的可视化产品概念设计系统的实现[J].华南理工大学学报(自然科学版).1999,27(8):37-40.
[77]王勇军,徐明,胡守仁.面向对象知识库系统CAOBS/V1.2的可视化查询子系统[J].计算机研究与发展.1998,35(8):684-688.
[78]袁守谦,邢曼华,李都宏等.转炉冶炼专家系统开发研究[J].西安建筑科技大学学报（自然科学版）.2012,44(1):137-140.
[79]谢书明,陈昌,丁惜瀛.基于BP神经网络的转炉炼钢终点预报[J].沈阳工业大学学报.2007,29(6):707-710.
[80]韩敏,张俊杰,赵耀等.基于模糊加权的转炉炼钢磷分配比计算模型[J].冶金自动化.2010,34(3):14-18.
[81]蔡煜东,程兆年,陈念贻等.遗传程序设计用于工业调优——炼钢转炉炉龄预测[J].自动化学报.1997,23(1):50-56.
[82]张辉宜,周奇龙,袁志祥等.样本自选择回归分析算法在转炉炼钢中的应用[J].钢铁研究学报.2011,23(12):5-8.
[83]陈家祥.钢铁冶金学(炼钢部分)[M].北京:冶金工业出版社,1999.
[84]顾宏.转炉过程模型与控制技术[J].江苏冶金.2003,31(4):8-10.
[85] Ken-Iwamura，Macao FurusawaMasakazu Miyamoto. New endpoint control system withauto-parameter-turning in BOF[C].Steelmaking Conference Proceedings.1995:715-719.
[86] D.Anderson, C.M.Barnes, H.J.Whittaker. Fully dynamic process control of the BOS in BritishSteel[C].Steelmaking Conference Proceedings.1991:379-387.
[87] Teruki Makino，Shigeru Omiya, Nobukazu Kitagawa. Automatic operation of converters atmizushima works[C].Steelmaking Conference Proceedings.1989:67-71.
[88] Hiroshi Yamane, Michitaka Kanemoto,Tooru Yoshida. Development of expert system andonline sensor for BOF process[C].Steelmaking Conference Proceedings.1991:453-458.
[89]周子懿,将慎言. LD转炉动态控制CRM模型[J].冶金自动化:1989,13(2),3-8.
[90]史战东.转炉终点控制模型的比较分析和改进研究[D].重庆大学硕士论文,2008,6.
[91]雷新泉,雷曼.转炉炼钢静态模型的初步探讨[J].钢铁研究,1994(2):8-12.
[92]黄今侠.转炉炼钢终点静态控制预测模型[D].天津大学硕士论文,2005,6.
[93]胡燕,何腊梅.转炉炼钢终点控制模型的方法研究[J].钢铁技术.2009,(6):14-16.
[94]刘浏.转炉全自动吹炼技术[J].冶金自动化.1999,4:1-6.
[95]代友训.转炉炼钢终点准动态控制系统[D].重庆大学硕士论文,2007,4.
[96]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.
[97]谢书明,陶钧,柴天佑.基于神经网络的转炉炼钢终点控制[J].控制理论与应用.2003，20(6):903-907.
[98] Akcayol, M. Ali, Cinar, Can. Artificial neural network based modeling of heated catalyticconverter performance[J]. Applied Thermal Engineering.2005,25:2341-2350.
[99]杨立红,刘浏,何平.基于自适应模糊神经网络系统的转炉终点磷的预报控制模型[J].钢铁研究学报.2002,14(4):47-51.
[100]田民乐,刘少民.基于模糊神经网络的炼钢炉静态建模[J].北京科技大学学报.1998,20(2)：136-139.
[101] Abbas, Ghulam,Farooq, Umar; Asad, Muhammad Usman.Application of neural networkbased model predictive controller to power switching converters[C].Proceedings of the2011International Conference and Workshop on the Current Trends in InformationTechnology,.2011,132-136.
[102] Yang, Lihong,Liu, Liu; He, Ping. Control of carbon content and temperature at end point forconverter process based on2-output neural network[J]. Kang T'ieh/Iron and Steel(Peking).2002,37(11):13-15.
[103] Wang Jianhui,Xu, Lin; Fang, Xiaoke ect.Class of GA-RBF neural network control for theBOF steelmaking static model[J].Journal of Southeast University (Natural ScienceEdition).2005,35(SUPPL):90-94.
[104] K Hornik K, M Stinchcombe H White.Multilayer feed forward network are universalapproximators[J]. Neural Networks,1989,(2):359-366.
[105]王小平,曹立明.遗传算法理论、应用与软件实现[M].西安:西安交通大学出版社,2002.(1):73-78.
[106]刘杰,王媛.一种高效混合遗传算法[J].河海大学学报.2002,30(2):49-53.
[107]郭彤城,慕春棣.并行遗传算法的新进展[J].系统工程理论与实践,2002,(2):15-21..
[108]侯格贤,吴成柯.遗传算法的性能分析[J].控制与决策.1999,14(3):257-260.
[109] Díaz-Cruz M, Morales, R.D.,Olivares etc.Physical and mathematical models of gas-liquiddynamics in BOF converters[C]. Steelmaking Conference Proceedings,.2002,85:737-748.
[110] Yuhendri, Muldi, Ashari, Mochammad; Purnomo, M.H.Linear Quadratic Regulator designfor modular matrix converter using Genetic Algorithm[C].2011IEEE3rd InternationalConference on Communication Software and Networks.2011,175-179.
[111]樊莉萍,王成钢,张建伟等.转炉吹炼实时控制专家系统RESC的设计与实现[J].计算机研究与发展.1997,34(6):432-438.
[112]陶钧,柴天佑,李小平等.转炉炼钢智能控制方法及应用[J].控制理论与应用.2001.18(S1):129-133.
[113]襄祖安.转炉炼钢造渣操作指导专家系统[J].上海金属.13(5):45-49.
[114]樊俊飞,李永和,许春雷等.宝钢转炉吹炼控制模拟在线专家系统[J].北京科技大学学报.1995,17(S1):6-11.
[115] Hofinger, Stephan Hubmer,Rudolf etc. Steel expert takes command optimized performance onBOF converter[J]. AISTech2012Iron and Steel Technology Conference andExposition.2012,925-935.
[116]袁守谦,邢曼华,李都宏等.转炉冶炼专家系统开发研究[J].西安建筑科技大学学报（自然科学版）2012.44(1):137-140.
[117]周双喜.一种用于转炉炉口微压差控制的混合控制策略[J].自动化与仪器仪表.2011,(6):14-16.
[118]于立业,徐林,王建辉等.基于声强的转炉氧枪枪位控制专家系统[J].冶金自动化.2005，(5):11-14.
[119] Deo Brahma, Balakrishnan V. Application of model predictive control in a dynamic system:An application to BOF steelmaking process[C]. AISTech2009-Proceedings of the Iron andSteel Technology Conference.2009,1:801-810.
[120] Ceriani Alfredo,Aprile Giovanni, ScipoloVittorio etc. Dynamic modeling of the BOF forendpoint prediction using EFSOP technology results and implementation at riva taranto[C].AISTech2010-Proceedings of the Iron and Steel Technology Conference.2010,997-1003.
[121] Huber J.-C,Lehmann J.,Cadet R. Comprehensive dynamic model for BOF process: A glimpseinto thermal efficiency mechanisms[J].Revue de Metallurgie.2008,105(3):121-126.
[122] Graveland-Gisolf E., Mink P.,Overbosch A etc. Slag-droplet model: A dynamic tool tosimulate and optimise the refining conditions in BOF[J]. Steel Research.2003,74(3):125-130.
[123]史成钢.转炉控制动态校正模型的分析与改进[J]鞍钢技术.1992,(5):36-41.
[124] Kuo-Chih CHOU,Uday B.PAL,Ramana G.REDDY.A general model for BOP decarburization[J].ISLJ international.1993.33(8):862-867.
[125]李彦平,潘德惠.BOF系统的炉气分析及其自动控制[J].控制与决策.1988,(2):7-10.
[126]张润宇,肖兵,张文弟.转炉钢水碳含量估计[J].自动化学报.1993,19(3):18-20.
[127] S.Y.Yun, K.S.Chang, S.M.Byun. Dynamic prediction using neural network for automation ofBOF process in steel industry[J].I&SM.1996,8:37-42.
[128]干勇.炼钢—连铸新技术800问[M].北京:冶金工业出版社.2003,6-7.
[129]沈昶,施雄梁,汤曙光等.烟气分析动态控制炼钢在马钢的应用[C].2005中国钢铁年会论文集,162–165.
[130] Robertson K.J., Balajee S.R.,Shearer, J.M. etc. Sublance dynamic control operation and itseffect on the performance of the Inland Steel Company's No.4BOF shop[J]. I&SM.1989,16(8):36-42.
[131] Takemura Yozo,Fukuda Shigemi,Saito Toyokazu etc. BOF dynacmic control using sublancesystem[J]. Nippon Steel Technical Report.1978,(11):57-68.
[132] Spanjers M.,Glitscher W. Sublance-based on-line slag control in BOF steelmaking[J].AISTech2005-Iron and Steel Technology Conference Proceedings.2005,1:723-728.
[133] Friedl Erich,Kaiser Heinz Peter. Automatic blowing process in BOF and direct tapping usingthe sublance system[J]. MPT. Metallurgical plant and technology.1990,13(1):28-32.
[134]吴健鹏,刘先同,何金平等.150t转炉副枪及自动炼钢系统的应用[J].武钢技术.2011,49(3):13-18.
[135]王忠刚,任科社,刘忠建.副枪技术在莱钢120t转炉上的应用[J].中国冶金.2009,19(11):30-32.
[136] Gruner, H., Wiemer, H.-E., Fix, W. etc. New metallurgical insight into BOF steelmaking andimproved process control using sublance techniques and bottom gas stirring[J]. I&SM.1985,12(3):31-36.
[137] Nashiwa H.,Mizuno T., Ohi J. etc. Effective use of returned LD slag and dolomite andoperation with sublance system[J].Ironmaking and Steelmaking.1978,5(3):95-102.
[138]左康林,邹俊苏,孙晓辉等.转炉副枪测量与成分预报技术[J].炼钢.2009,25(2):59-61.
[139]陈忠清,黄林湘.HFS系列转炉副枪测头研制与应用[J].计量装置及应用.2005,15(3):23-25.
[140]陈重丽,张妙法,陈业泰等.转炉副枪用测铁水液面探头的研制[J].宝钢技术.1989,(3):33-34.
[141]王胜.BOF副枪控制和数据处理.冶金自动化[J].2006,(4):29-33.
[142]章文超.转炉副枪系统型式与国产化[J].世界钢铁.2010,(2):23-26.
[143]汪大洲.国外转炉副枪及其探头[J].冶金自动化.1977,(3):110-117.
[144] Romanovskii Oleg A.,Matvienko Gennadii G.,Kharchenko Olga V. etc. The use of frequencyconverter of femtosecond laser radiation in broadband lidar gas analysis of atmosphere[J].Proceedings of SPIE-The International Society for Optical Engineering.2006,6522-6524.
[145] Niebuhr, M., Gabriel, A.,Koch, M.H.J..Analysis of fluorescence effects in a position-sensitivegas detector using a time-stamp time-to-digital converter[J]. Nuclear Instruments andMethods in Physics Research.2003,510(3):309-317.
[146] Mabuchi Masaki,Kokubu Haruo,Nakato Hakaru etc. Numerical analysis of the gas flow andcombustion reaction in converter[J].Journal of the Iron and Steel Institute ofJapan.1989,75(7):1139-1145.
[147]刘文,杨宪礼,白彦.转炉采用炉气分析法进行动态控制[J].炼钢.2003,19(5):48-51.
[148]万雪峰,张贵玉,林东等.转炉炉气成分变化规律的初步研究[J].中国冶金.2006,16(1):23-26.
[149]胡志刚,何平,刘浏等.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.
[150]袁建路,董中奇,黄伟青等.对转炉炉气在线检测的数学模拟分析[J].物理测试.2012,31(1):13-16.
[151]丁长江,刘国平,周俐.利用炉气CO浓度曲线监控转炉造渣操作[J].中国冶金.2007,17(10):16-19.
[152] Díaz-Cruz M,Morales R.D,Olivares etc.Physical and mathematical models of gas-liquiddynamics in BOF converters[C].2002Proceedings-Ironmaking Conference.2002,825-836.
[153] O'Shaughnessy Earl J.,Bicknese Eugene H. Improved BOF practice through waste gssanalysis[C]. Proceedings-National Open Hearth and Basic Oxygen SteelConference.1974,5:169-177.
[154]石知机,汪国才,李应江.炉气分析终点控制技术在马钢转炉的应用[J].钢铁.2007,42(4):24-26.
[155]张贵玉,万雪峰,林东等.转炉炉气分析动态控制技术的应用[J].钢铁.2007,42(9):29-32.
[156] Iso, Hei-ichiro, Jyono, Yutaka etc. Dynmic refining control by analysis of exhaust gas fromLD converter[J].Transactions of the Iron and Steel Institute of Japan.1987,27(5):351-359.
[157] Takawa Takeshi,Katayama Katsumi,Katohgi Ken etc. Analysis of converter process variablesfrom exhaust gas[J]. Transactions of the Iron and Steel Institute of Japan.1988,28(1):59-67.
[158]胡志刚,刘浏.炉气分析在转炉动态控制中的应用[J].钢铁研究学报.2002,13(3):68-73.
[159] Suraj, Zbigniew. Discovery of concurrent data models from experimental tables: a rough setapproach. Fundamenta Informaticae.1996,28(3):353-376.
[160] Grzymala-Busse J W. LERS: A System of Knowledge Discovery Based on Rough Sets[C].Proc of5th Int Workshop RSFD’96.Tokyo,1996,443-444.
[161]樊俊飞,李永如,姚海石.宝钢转炉吹炼控制模拟在线专家系统[J].宝钢技术.1996，4：50-54
[162]任卫国.基于粗糙集理论的机器人视觉跟踪系统研究[D].河北工业大学,2007.
[163] Ramanna Sheela, Peters James F., Ahn Taechon.Software quality knowledge discovery: Arough set approach[C].Proceedings-IEEE Computer Society's International ComputerSoftware and Applications Conference.2002,1140-1145.
[164] Nguyen, Tuan Trung.Rough set approach to domain knowledge approximation[J].Fundamenta Informaticae.2004,59(2-3):261-270.
[165]张文修,吴伟志,梁吉业.粗糙集理论与方法[M].北京:科学出版社,2001.
[166]张勇.粗糙集-神经网络智能系统在浮选过程中的应用[D].大连理工大学博士学位论文,2006.
[167]赵卫东,陈国华.粗集与神经网络的集成技术研究[J].系统工程与电子技术.2002,24（10）：103-107.
[168] J. Ilona, M. Chris, W. Tim.An investigation into the application of neural networks, fuzzylogic, genetic algorithms, and rough sets to automated knowledge acquisition forclassification problems[J]. Neurocomputing.1999,24(1-3):37-54.
[169]陈遵德. Rough Set神经网络智能系统及其应用[J].模式识别与人工智能.1999,12(1):1-5.
[170] Ahn B.S，Cho S. S，Kim C. Y..The integrated methodology of rough set theory and artificialneural network for business failure prediction[J].Expert system withApplication.2000,18:65-74.
[171] Szcauka M.S. Rough set methods for constructing artificial neural networks[J]. Americansociety of mechanical engineers.1996,79(7):9-14.
[172] Hashei R. R，LeBlance L. A，etl. Hybired intelligent system for predicting bank holdingstructure[J]. European Journal of Operational Research,1999,109(2):390-402.
[173]胡寿松,何亚群.粗糙决策理论与应用[M].北京:北京航空航天大学出版社,2006.
[174] Pawlak Z. Rough sets[J]. lnt. J. of information and computer science.1982,11:341-356.
[175]王钰,苗夺谦.关于Rouge Set理论与应用的综述[J].模式识别与人工智能.1996,9(4):337-344
[176]刘清,黄兆华,姚力文.Rough集理论:现状与前景[J].计算机科学.1997,24(4):1-5.
[177]韩祯祥,张琦,文福栓.粗糙集理论及其应用综述[J].控制理论与应用.1999,16(2):153-157.
[178]潘丹.基于粗糙集理论的混合智能知识处理研究[D].华南理工大学博士学位论文,2001.
[179] A. Roy,S. K. Pal.Fuzzy discretization of feature space for a rough set calssifier[J]. PatternRecognition Letters.2003,24(6):895-902.
[180] M. R. Chmielewski, J. W. Grzymala-Busse, et. al.The rule induction system LERs一Aversion for personal computer[J]. Found. Computer Decision Sci.1993.18(3-4):181-212.
[181]王国胤. Rough集理论与知识获取[M].西安交通大学出版社.2001.
[182] A. Roy，S. K. Pal. Fuzzy discretization of feature space for a rough set calssifier[J]. PatternRecognition Letters.2003,24(6):895-902
[183] M. R. Chmielewski, J. W. Grzymala-Busse. The rule induction system LERs一A version forpersonal computer[J].Found. Computer Decision Sci.1993.18(3-4):181-212.
[184]郭志懋,周傲英.数据质量和数据清洗研究综述[J].软件学报.2002,13(11):2076-2082.
[185]刘叶玲,朱艳伟.加权数据融合算法及其应用举例[J].西安科技大学学报.2005,25(2)：253-255.
[186]朱学锋,韩荣阁,杨若红.基于模糊预测系统的观测数据野值剔除方法[J].系统工程与电子技术.2006,28(3):478-482.
[187]李梦奇,白晓军,匡同春等.工程技术领域等精度数据异常值判定系统[J].计量技术.2006,3：57-59.
[188] Amitava R,Sankar K. P.Fizzy discretization of feature space for a rough set classifer.[J]Pattern Recognition Letters,200324:895-902.
[189]谢洪,程浩忠,牛东晓.基于信息嫡的粗糙集连续属性离散化算法[J].计算机学报.2005,28(9):1570-1574.
[190]刘胜军,杨学兵,蔡庆生.关系数据库中概念层次自动提取算法研究[J].计算机应用研究.1999,(12):15-17.
[191]曾黄麟.粗集理论及其应用[M].重庆:重庆大学出版社,1998.
[192]张文修,吴伟志.粗糙集理论介绍和研究综述[J].模糊系统与数学.2000.14(4):84-89.
[193]程岩,黄梯云.信息系统中一种面向粗糙集的数据挖掘方法[J].情报学报.2001,20(1),90-99.
[194]杨敏,沈春林.Matlab神经网络工具箱编程和Delphi对其调用[J].计算机工程，2001,27(11):92-94.
[195]田雨波.混合神经网络技术[M].北京:科学出版社.2009.
[196]丛爽.面相Matlab工具箱的神经网络理论与应用[M].北京:中国科学技术大学出版社.1998.
[197]杨建刚.人工神经网络实用教程[M].杭州:浙江大学出版社.2001.
[198]张磊,胡春,钱锋等．BP算法局部极小问题改进的研究进展[J].工业控制计算机.2004，17(9):33-50.
[199] K Hornik K, M Stinchcombe H White.Multilayer feed forward network are universalapproximators[J]. Neural Networks.1989,(2):359-366.
[200]冯明霞,李强,邹宗树.转炉终点预测模型中异常数据检验的研究[J].中国冶金.2006,16(9)：27-31.