基于粗糙集—思维进化算法的应用研究
|
摘要
本文首先深入分析了粗糙集理论的思想精髓、特点,简要介绍了它与模糊逻辑、神经网络、进化算法等软计算方法的融合,并综述了粗糙集在智能控制中应用现状。
由于粗糙集理论方法分析的是有限维的离散化数据表,因此在利用粗糙集理论进行数据挖掘时,需要将数据进行离散归一化。对于一个包含大量连续属性值的原始数据库,如何根据需要合理对数据进行归一化处理应该是粗糙集理论中值得注意的一个问题。
针对这一点,应用粗糙集理论从数据中挖掘知识和思维进化算法全局寻优的特点,本文首次将两者相结合,利用思维进化算法搜索离散归一化合理分割点的位置。提出了考虑全部条件属性值的全局离散化方法,避免了对单一条件属性进行局部离散化所产生的不合理的离散分割点,进而产生不一致性规则。利用本文提出的算法对水泥窑输入输出数据进行分析处理,并对典型的水泥窑模糊建模问题进行了求解。实验结果表明了该方法简单易行,省去了复杂的手工试凑约简。
进而本文将这种方法应用到工业过程中复杂时变大滞后对象上,提出一种基于粗糙集和思维进化算法的模糊控制器的设计方法。该方法通过研究“专家”控制下的被控对象的输入输出特性,学习专家的控制规律,提供了一种将专家领域知识转化为模糊控制规则的数学方法。这种方法极大地提高了智能控制系统的机器智商。
This paper deeply analyzes basic ideas and pith of Rough Set theory, introduces its combination with other soft computing methods such as evolution algorithms, fuzzy sets, neural networks, and then reviews its current application in Intelligent Control systems.Rough Set theory method analyzes limited-dimension discrete datasheet, so we must discretize data in database. But for an original database with large continuous attributes values, how to discretize data reasonably is a noticeable problem.Aiming at this condition, by using the characteristics of rough set which can explore knowledge from data and mind evolutionary algorithm which can find the best point globally, this paper combines the two methods for the first time, and used mind evolutionary algorithm to search reasonable split points. Considering the whole condition attributes values, this paper proposes a global discretization approach to avoid creating unreasonable discrete split points that appeared in discretizing each
continuous attribute independently. By using the method in this paper, the input and output data of cement stove were analyzed, and the fuzzy model of cement stove is established. The experiment shows that the method is simple and rapid and can elide complex handwork reduction.Applying this method into the complex controlled object with large time delay and characteristic of time varying, a fuzzy controller based on rough set and mind evolutionary algorithm is presented in this paper. By studying input and output characters of the controlled object, which is under the control of "experts", rough set and the mind evolutionary algorithm together provide an efficient method to convert expert knowledge from data to fuzzy rules. This method will largely enhance the MIQ of the intelligent system.
由于粗糙集理论方法分析的是有限维的离散化数据表,因此在利用粗糙集理论进行数据挖掘时,需要将数据进行离散归一化。对于一个包含大量连续属性值的原始数据库,如何根据需要合理对数据进行归一化处理应该是粗糙集理论中值得注意的一个问题。
针对这一点,应用粗糙集理论从数据中挖掘知识和思维进化算法全局寻优的特点,本文首次将两者相结合,利用思维进化算法搜索离散归一化合理分割点的位置。提出了考虑全部条件属性值的全局离散化方法,避免了对单一条件属性进行局部离散化所产生的不合理的离散分割点,进而产生不一致性规则。利用本文提出的算法对水泥窑输入输出数据进行分析处理,并对典型的水泥窑模糊建模问题进行了求解。实验结果表明了该方法简单易行,省去了复杂的手工试凑约简。
进而本文将这种方法应用到工业过程中复杂时变大滞后对象上,提出一种基于粗糙集和思维进化算法的模糊控制器的设计方法。该方法通过研究“专家”控制下的被控对象的输入输出特性,学习专家的控制规律,提供了一种将专家领域知识转化为模糊控制规则的数学方法。这种方法极大地提高了智能控制系统的机器智商。
This paper deeply analyzes basic ideas and pith of Rough Set theory, introduces its combination with other soft computing methods such as evolution algorithms, fuzzy sets, neural networks, and then reviews its current application in Intelligent Control systems.Rough Set theory method analyzes limited-dimension discrete datasheet, so we must discretize data in database. But for an original database with large continuous attributes values, how to discretize data reasonably is a noticeable problem.Aiming at this condition, by using the characteristics of rough set which can explore knowledge from data and mind evolutionary algorithm which can find the best point globally, this paper combines the two methods for the first time, and used mind evolutionary algorithm to search reasonable split points. Considering the whole condition attributes values, this paper proposes a global discretization approach to avoid creating unreasonable discrete split points that appeared in discretizing each
continuous attribute independently. By using the method in this paper, the input and output data of cement stove were analyzed, and the fuzzy model of cement stove is established. The experiment shows that the method is simple and rapid and can elide complex handwork reduction.Applying this method into the complex controlled object with large time delay and characteristic of time varying, a fuzzy controller based on rough set and mind evolutionary algorithm is presented in this paper. By studying input and output characters of the controlled object, which is under the control of "experts", rough set and the mind evolutionary algorithm together provide an efficient method to convert expert knowledge from data to fuzzy rules. This method will largely enhance the MIQ of the intelligent system.
引文
[1] P.J.Antsaklis. Defining Intelligent Control-Report of Task Force on Intelligent Control. IEEE Control Systems Magazine, vol.14, No.3, 4-5, 1994, 58-66.
[2] K. M.Passino. Bridging the Gap between Conventional and Intelligent Control. IEEE Control Systems Magazine, vol.13, No.2, 1993, 12-18.
[3] R.J.Marks. Intelligence: Computational Versus Artificial. IEEE Trans on Neural Networks, vol.4, No, 1993, 737-739.
[4] K.J.Astrom, Thomas J. Meavoy Intelligent Control. J. Proe. Cont. 1992, (3): 115-127.
[5] 郑应平.从IFAC'96世界大会看自动控制发展的若干动向[J].自动化学报.1997,123(3):428-431.
[6] 谢克明,侯宏仑.复杂系统的智能控制方法[J].太原理工大学学报,1998,29(6):568-576.
[7] 谢克明,南建峰.基于模糊神经网络的辨识与控制技术的现状及展望[J].太原理工大学学报,1998,29(1):8-12.
[8] Xie Keming, Nan Jianfeng, T.Y. Lin.. A new fast fuzzy -neural feedback in application to temperature control. In proc. Of the 14th world congress of jinternational federation of automatic jcontrol (IFAC'99), 1999, Beijing P.R. china: 339-334.
[9] Ding Fang, Xie Keming. A method for the fault diagnosis of digital circuits based on the technique of the fuzzy-neural network system. In proc. of 4th international conference on electronic measurement and instruments. Harbin, China, 1999: 627-631.
[10] Xie Keming, T.Y.Lin, Jianfeng Nan. A fuzzy neural network based on the TS model with dynamic consequent parameters and application to steam temperature control system. In proc. Of the 8th international fuzzy system association world congress (IFSA'99), Taipei, Taiwan. 690-694.
[11] Keming Xie, Changhua Mou, Gang Xie. A MEBML-based adaptive fuzzy logic controller [C]. 2000 IEEE International Conference on Industrial Electronics, Control and Instrumentation, 21st Century Technologies and Industrial Opportunities, October 22-28, 2000, Nagoya Congress Center, Nagoya, Japan, 1492-1496.
[12] Keming Xie, Changhua Mou, Gang Xie. A new MEBML-based algorithm for adjusting parameters on-line [C]. Proc. of 2000 5th International Conference on Signal Processing (ICSP 2000, WCC2000), Aug. 21-25, 2000, Beijing, China, 1718-1721.
[13] Keming Xie, Yonggui Du, Chengyi Sun. Application of the Mind-Evolution-Based Machine Learning in Mixture-Ratio Calculation of Raw Materials Cement [C]. Proc. of the 3rd World Congress on Intelligent Control and Automation, Jun 28-July 2, 2000, Hefei, China, 132-134.
[14] Keming Xie, Changhua Mou, Gang Xie. The multi-parameter combination mind-evolutionary-based machine learning and its application [C]. Proceedings. of 2000 IEEE International Conference on Systems, Man, and Cybernetics (SMC2000), 2000.10, Music City, Sheraton, Nashville, Tennessee, USA: 183-187.
[15] 王克宏等.知识工程与知识处理系统[M].清华大学出版社,1994.
[16] Pawlak. Z et al. Rough sets. Communications of ACM, 1995, 38(11): 89-95.
[17] Pawlak Z. Rough sets. International Journal of Information and Computer Science, 1982, (11): 341-356.
[18] Pawlak. Z. Rough set-theoretical aspects of reasoning about data. Dordrecht: Kluwer Academic Publishers, 1991.
[19] Slowinski R. Intelligent decision support-handbook of applications and advances of the rough sets theory. Dordrecht: Kluwer Academic Publishers, 1992.
[20] Didier DUBIOS, Henri PRADE. Putting Rough Sets and Fuzzy Sets Together. Int. J. General Systems, 1990, Vol.17, 191-209.
[21] Z.Pawlak. Rough sets and their applications. Microcomputer Applications. Vol. 13, No.2, 1994.
[22] Special Issue. Scientific discovery. Artificial intelligence, 1997; 91(2).
[23] What Computers Still Can't Do: five reviews and response and a response. Artificial Intelligence, 1996; 80(1).
[24] Roger Penrose. The Emperor's New Mind; Concerning Computers' Minds, and The Laws of Physics. Oxford; Oxford Clniversity Press, 1989.
[25] Special Issue. Artificial Intelligence Research in Japan. Artificial Intelligence. 1997; 91(1).
[26] Special Volume on Frontiers in Problem Solving: Phase Transitions and Complexity, Artificial Intelligence, 1996; 81 (1-2).
[27] 王钰,张钻.Rough set约简与数据浓缩.中国自动化学会七属一次理事会暨学术年会论文集.天律:1997.
[28] 田玉楚,符雪桐,吕勇哉,席裕庚,张钟俊.非线性控制和优化系统中的混沌运动.控制与决策.1995;10(1):1-7.
[29] 陈关荣.控制非线性动力系统的混沌现象.控制理论与应用,1997;14(1):1-6.
[30] Showron,A, and Grzymala-Busse, J.W.Fron rough set theory to evidence theory. In Advances in the Dempster-Shafer Theory of Evidence. R.R.Yaeger, M.Fedtixzzi, and J.Kacprzyk, Eds.Wiley, New York: 1994; 193-236.
[31] Skowron, A. and Rauszer,C. The discernibility matrices and functions in information systems. Intelligent decision support, handbook of advances and applications of the rough set theory, R.Slowinski Ed. Kluwev, Dordrecht, Netherlands: 1992; 331-362.
[32] Ziarko, W.Ed. Rough sets, fuzzy sets and knowledge discovery. In Proceedings of RSKD'94 Workshop (Bauff) Springev-Verlag, Berlin: 1994.
[33] Ziarko,W. The discovery, analysis and representation of data dependencies in databases. Knowledge Discovery in Databases, G.Piatetsky-Shapiro, and W.J.Frawley, Eds. AAAI Press/MIT Press, 1991; 177-195.
[34] Szladow,A. and Ziarko,W. Rough sets: Working with imperfect data. AIExpert7.1993; 36-41.
[35] Keming Xie, Zehua Chen. Application of rough sets in intelligent control. 4th international symposium on test and measurement (ISTM/2001). 291-294.
[36] 谢克明,杨静.粗糙集理论及其在智能控制领域的应用前景[J].太原理工大学学报,1999,(4):338-342.
[2] K. M.Passino. Bridging the Gap between Conventional and Intelligent Control. IEEE Control Systems Magazine, vol.13, No.2, 1993, 12-18.
[3] R.J.Marks. Intelligence: Computational Versus Artificial. IEEE Trans on Neural Networks, vol.4, No, 1993, 737-739.
[4] K.J.Astrom, Thomas J. Meavoy Intelligent Control. J. Proe. Cont. 1992, (3): 115-127.
[5] 郑应平.从IFAC'96世界大会看自动控制发展的若干动向[J].自动化学报.1997,123(3):428-431.
[6] 谢克明,侯宏仑.复杂系统的智能控制方法[J].太原理工大学学报,1998,29(6):568-576.
[7] 谢克明,南建峰.基于模糊神经网络的辨识与控制技术的现状及展望[J].太原理工大学学报,1998,29(1):8-12.
[8] Xie Keming, Nan Jianfeng, T.Y. Lin.. A new fast fuzzy -neural feedback in application to temperature control. In proc. Of the 14th world congress of jinternational federation of automatic jcontrol (IFAC'99), 1999, Beijing P.R. china: 339-334.
[9] Ding Fang, Xie Keming. A method for the fault diagnosis of digital circuits based on the technique of the fuzzy-neural network system. In proc. of 4th international conference on electronic measurement and instruments. Harbin, China, 1999: 627-631.
[10] Xie Keming, T.Y.Lin, Jianfeng Nan. A fuzzy neural network based on the TS model with dynamic consequent parameters and application to steam temperature control system. In proc. Of the 8th international fuzzy system association world congress (IFSA'99), Taipei, Taiwan. 690-694.
[11] Keming Xie, Changhua Mou, Gang Xie. A MEBML-based adaptive fuzzy logic controller [C]. 2000 IEEE International Conference on Industrial Electronics, Control and Instrumentation, 21st Century Technologies and Industrial Opportunities, October 22-28, 2000, Nagoya Congress Center, Nagoya, Japan, 1492-1496.
[12] Keming Xie, Changhua Mou, Gang Xie. A new MEBML-based algorithm for adjusting parameters on-line [C]. Proc. of 2000 5th International Conference on Signal Processing (ICSP 2000, WCC2000), Aug. 21-25, 2000, Beijing, China, 1718-1721.
[13] Keming Xie, Yonggui Du, Chengyi Sun. Application of the Mind-Evolution-Based Machine Learning in Mixture-Ratio Calculation of Raw Materials Cement [C]. Proc. of the 3rd World Congress on Intelligent Control and Automation, Jun 28-July 2, 2000, Hefei, China, 132-134.
[14] Keming Xie, Changhua Mou, Gang Xie. The multi-parameter combination mind-evolutionary-based machine learning and its application [C]. Proceedings. of 2000 IEEE International Conference on Systems, Man, and Cybernetics (SMC2000), 2000.10, Music City, Sheraton, Nashville, Tennessee, USA: 183-187.
[15] 王克宏等.知识工程与知识处理系统[M].清华大学出版社,1994.
[16] Pawlak. Z et al. Rough sets. Communications of ACM, 1995, 38(11): 89-95.
[17] Pawlak Z. Rough sets. International Journal of Information and Computer Science, 1982, (11): 341-356.
[18] Pawlak. Z. Rough set-theoretical aspects of reasoning about data. Dordrecht: Kluwer Academic Publishers, 1991.
[19] Slowinski R. Intelligent decision support-handbook of applications and advances of the rough sets theory. Dordrecht: Kluwer Academic Publishers, 1992.
[20] Didier DUBIOS, Henri PRADE. Putting Rough Sets and Fuzzy Sets Together. Int. J. General Systems, 1990, Vol.17, 191-209.
[21] Z.Pawlak. Rough sets and their applications. Microcomputer Applications. Vol. 13, No.2, 1994.
[22] Special Issue. Scientific discovery. Artificial intelligence, 1997; 91(2).
[23] What Computers Still Can't Do: five reviews and response and a response. Artificial Intelligence, 1996; 80(1).
[24] Roger Penrose. The Emperor's New Mind; Concerning Computers' Minds, and The Laws of Physics. Oxford; Oxford Clniversity Press, 1989.
[25] Special Issue. Artificial Intelligence Research in Japan. Artificial Intelligence. 1997; 91(1).
[26] Special Volume on Frontiers in Problem Solving: Phase Transitions and Complexity, Artificial Intelligence, 1996; 81 (1-2).
[27] 王钰,张钻.Rough set约简与数据浓缩.中国自动化学会七属一次理事会暨学术年会论文集.天律:1997.
[28] 田玉楚,符雪桐,吕勇哉,席裕庚,张钟俊.非线性控制和优化系统中的混沌运动.控制与决策.1995;10(1):1-7.
[29] 陈关荣.控制非线性动力系统的混沌现象.控制理论与应用,1997;14(1):1-6.
[30] Showron,A, and Grzymala-Busse, J.W.Fron rough set theory to evidence theory. In Advances in the Dempster-Shafer Theory of Evidence. R.R.Yaeger, M.Fedtixzzi, and J.Kacprzyk, Eds.Wiley, New York: 1994; 193-236.
[31] Skowron, A. and Rauszer,C. The discernibility matrices and functions in information systems. Intelligent decision support, handbook of advances and applications of the rough set theory, R.Slowinski Ed. Kluwev, Dordrecht, Netherlands: 1992; 331-362.
[32] Ziarko, W.Ed. Rough sets, fuzzy sets and knowledge discovery. In Proceedings of RSKD'94 Workshop (Bauff) Springev-Verlag, Berlin: 1994.
[33] Ziarko,W. The discovery, analysis and representation of data dependencies in databases. Knowledge Discovery in Databases, G.Piatetsky-Shapiro, and W.J.Frawley, Eds. AAAI Press/MIT Press, 1991; 177-195.
[34] Szladow,A. and Ziarko,W. Rough sets: Working with imperfect data. AIExpert7.1993; 36-41.
[35] Keming Xie, Zehua Chen. Application of rough sets in intelligent control. 4th international symposium on test and measurement (ISTM/2001). 291-294.
[36] 谢克明,杨静.粗糙集理论及其在智能控制领域的应用前景[J].太原理工大学学报,1999,(4):338-342.
© 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 |