汽轮发电机组振动故障集成诊断网络模型及方法研究
|
摘要
随着国民经济的发展,我国大型汽轮发电机组的单机容量日益增大,这对机组可用率、运行效率、安全性、可靠性与经济性提出了更高的要求。因此,研究汽轮发电机组振动故障诊断技术对其安全稳定运行有着十分重要的理论意义和巨大的经济效益。本文在总结和借鉴前人有关汽轮发电机组状态监测和故障诊断研究的基础上,重点研究了基于模糊集、人工神经网络、粗糙集、遗传算法以及它们相互结合机制的诊断理论和方法,用已有的汽轮发电机组振动故障实例进行了验证,得出了一些具有实用价值的结论,并提出了可靠、实用的大型汽轮发电机组振动故障诊断的新方法。本文主要内容有:
1阐述了本课题研究的目的和意义,对汽轮发电机组振动故障的特点、机组在线监测和故障诊断技术的研究现状和方法以及模糊集、神经网络、粗糙集和遗传算法的发展及其在机组振动故障诊断中的应用进行了全面的综述。
2分析和研究了汽轮发电机振动故障的电气、机械和热力机理,提出采用模糊集理论对征兆数据进行规范化处理的方法,为进一步的智能诊断技术研究奠定基础。
3深入分析BP神经网络在理论和方法上存在的缺陷,提出采用遗传算法优化初始网络权重,将遗传算法与BP神经网络有机地结合起来,迅速得到BP神经网络最佳的初始权值矩阵,并成功地运用于汽轮发电机组振动故障诊断系统。
4通过对粗糙集理论的深入分析,提出改善传统粗糙集约简抗干扰属性影响差的方法和基于遗传算法的粗糙集约简算法。仿真结果表明,该方法提高了粗糙集约简提取诊断规则的准确性和效率,能较好地满足诊断规则提取的技术要求,并成功地运用于汽轮发电机组振动故障诊断系统。
5针对大型汽轮发电机组振动故障的复杂性、非线性、影响因素多等特点,首次提出基于粗糙集理论的诊断规则分层发现方法,在诊断实例中取得了较好的效果。
6提出了基于粗糙集约简理论的汽轮发电机组振动故障诊断模糊神经网络,有效地压缩了神经网络的输入空间,经实例证明该方法能很好地对各层次的振动故障进行诊断。
7综合本文的研究成果,将模糊集、神经网络、遗传算法和粗糙集结合起来,首次提出了结合多种智能方法的汽轮发电机组振动故障集成诊断网络,通过故障实例诊断分析,效果良好,具有较强的实用价值。
With the development of national economy, the ever-growing capacity of large steam generator-set demands higher usability, security, reliability and economical efficiency. Thus the research to the technology of the vibration fault diagnosis in the stream generator-set is of vial significance to its safe function, and can bring us substantial benefits. Based on the former study of the condition monitor and fault diagnosis on stream generator-set, this dissertation focuses on fuzzy set theory, artificial neural network technology, rough set theory and the genetic algorithms and theories on their integration mechanism. Attested by the cases of vibration fault of the present steam generator-sets, this dissertation draws some feasible conclusions, and brings forth some reliable and practical new methods, which have further enriched and greatly improved the theories on the vibration fault monitor and diagnosis of the large stream generator-set. The main contents of this paper are described as follows:
1.The goals and meaning of this research are presented. It is a general survey to the feature of vibration faults of turbine generator-set, the present research and the research methods of on-line monitor and faults diagnosis, the development of Fuzzy Set Theory, Neural Network, Rough Set Theory and Genetic algorithms and their application in the generator-set vibration diagnosis.
2.Based on the analysis of the electric, mechanic and thermo theories of steam turbine generator-sets’ vibration faults, the application of the theory to the standardization of symptom data is put forward, which has provided a foundation for the research of intellectual diagnosis.
3.On the analysis of the weaknesses of the BPNN theory and methods, genetic algorithms is adopted to optimize the initial weight, and through their organic integration, the optimal weight matrix of BPNN can be obtained, which can be successfully applied to diagnose the vibration fault of steam generator-set.
4.On the analysis of rough set theory, the method to improve the traditional rough reduce weakness in avoiding the influence of interrupting attribute and the rough reduce algorithms based on genetic algorithm are brought forward. Suggested by simulation, this method has improved the exactness of technology requirement of diagnosis rules extraction and has been successfully used in vibration fault diagnosis in turbine generator-set.
5.In view of that vibration fault of large steam turbine generator-set has such features as complexity, non-linearity, multi influence factors and so on, the gradual discovery of diagnosis rules has been put forward and has been successfully used in actual fault diagnosis.
6.The fuzzy neural network of steam turbine generator-set’s vibration fault diagnosis based on rough set theory is brought forward, so as to compress the input dimension effectively, which has been proved to be successful by actual example.
7. Associated with achievements of this dissertation, the fuzzy set theory, neural network, genetic algorithm and rough set theory are integrated. The model of integrated diagnosis network of steam turbine generator-Set’s Vibration Faults is constructed, and analysis on practical fault case is carried out, the results show that the model has a fairly high practical value.
1阐述了本课题研究的目的和意义,对汽轮发电机组振动故障的特点、机组在线监测和故障诊断技术的研究现状和方法以及模糊集、神经网络、粗糙集和遗传算法的发展及其在机组振动故障诊断中的应用进行了全面的综述。
2分析和研究了汽轮发电机振动故障的电气、机械和热力机理,提出采用模糊集理论对征兆数据进行规范化处理的方法,为进一步的智能诊断技术研究奠定基础。
3深入分析BP神经网络在理论和方法上存在的缺陷,提出采用遗传算法优化初始网络权重,将遗传算法与BP神经网络有机地结合起来,迅速得到BP神经网络最佳的初始权值矩阵,并成功地运用于汽轮发电机组振动故障诊断系统。
4通过对粗糙集理论的深入分析,提出改善传统粗糙集约简抗干扰属性影响差的方法和基于遗传算法的粗糙集约简算法。仿真结果表明,该方法提高了粗糙集约简提取诊断规则的准确性和效率,能较好地满足诊断规则提取的技术要求,并成功地运用于汽轮发电机组振动故障诊断系统。
5针对大型汽轮发电机组振动故障的复杂性、非线性、影响因素多等特点,首次提出基于粗糙集理论的诊断规则分层发现方法,在诊断实例中取得了较好的效果。
6提出了基于粗糙集约简理论的汽轮发电机组振动故障诊断模糊神经网络,有效地压缩了神经网络的输入空间,经实例证明该方法能很好地对各层次的振动故障进行诊断。
7综合本文的研究成果,将模糊集、神经网络、遗传算法和粗糙集结合起来,首次提出了结合多种智能方法的汽轮发电机组振动故障集成诊断网络,通过故障实例诊断分析,效果良好,具有较强的实用价值。
With the development of national economy, the ever-growing capacity of large steam generator-set demands higher usability, security, reliability and economical efficiency. Thus the research to the technology of the vibration fault diagnosis in the stream generator-set is of vial significance to its safe function, and can bring us substantial benefits. Based on the former study of the condition monitor and fault diagnosis on stream generator-set, this dissertation focuses on fuzzy set theory, artificial neural network technology, rough set theory and the genetic algorithms and theories on their integration mechanism. Attested by the cases of vibration fault of the present steam generator-sets, this dissertation draws some feasible conclusions, and brings forth some reliable and practical new methods, which have further enriched and greatly improved the theories on the vibration fault monitor and diagnosis of the large stream generator-set. The main contents of this paper are described as follows:
1.The goals and meaning of this research are presented. It is a general survey to the feature of vibration faults of turbine generator-set, the present research and the research methods of on-line monitor and faults diagnosis, the development of Fuzzy Set Theory, Neural Network, Rough Set Theory and Genetic algorithms and their application in the generator-set vibration diagnosis.
2.Based on the analysis of the electric, mechanic and thermo theories of steam turbine generator-sets’ vibration faults, the application of the theory to the standardization of symptom data is put forward, which has provided a foundation for the research of intellectual diagnosis.
3.On the analysis of the weaknesses of the BPNN theory and methods, genetic algorithms is adopted to optimize the initial weight, and through their organic integration, the optimal weight matrix of BPNN can be obtained, which can be successfully applied to diagnose the vibration fault of steam generator-set.
4.On the analysis of rough set theory, the method to improve the traditional rough reduce weakness in avoiding the influence of interrupting attribute and the rough reduce algorithms based on genetic algorithm are brought forward. Suggested by simulation, this method has improved the exactness of technology requirement of diagnosis rules extraction and has been successfully used in vibration fault diagnosis in turbine generator-set.
5.In view of that vibration fault of large steam turbine generator-set has such features as complexity, non-linearity, multi influence factors and so on, the gradual discovery of diagnosis rules has been put forward and has been successfully used in actual fault diagnosis.
6.The fuzzy neural network of steam turbine generator-set’s vibration fault diagnosis based on rough set theory is brought forward, so as to compress the input dimension effectively, which has been proved to be successful by actual example.
7. Associated with achievements of this dissertation, the fuzzy set theory, neural network, genetic algorithm and rough set theory are integrated. The model of integrated diagnosis network of steam turbine generator-Set’s Vibration Faults is constructed, and analysis on practical fault case is carried out, the results show that the model has a fairly high practical value.
引文
付尚新,方泽南. 汽轮发电机组状态监测与故障诊断系统的现状及发展趋势. 清华大学学报[J],1995,135(s2):1-4
李伟清. 汽轮发电机故障检查分析与预防[M]. 北京:中国电力出版社,1996.
杨叔子,郑晓军. 人工智能与诊断专家系统[M]. 西安:西安交通大学出版社,1990:1~59。
高毅龙. 数据挖掘及其在工程诊断中的应用[D]. 博士学位论文,西安交通大学,2002.4.
史进渊,张兆鹤等. 大型汽轮机研究的某些新进展[J]. 动力工程,1999,19(2):1~7.
李录平,韩西京等. 火电机组故障诊断技术的现状与展望[J]. 电力情报,1997,3:1~3.
施维新. 汽轮发电机组振动[M]. 北京:水利电力出版社,1990.
郭桂蓉,谢维信. 模糊模式识别[M]. 北京:国防科技大学出版社,1993
J.S.米切尔. 机械故障的分析与诊断[M]. 北京:机械工业出版社,1990.
倪维斗,蒋东翔. 大型电站性能监测分析与诊断技术研究[J]. 动力工程,1997,17(3):1~5.
徐敏. 机械故障诊断技术的发展动向与问题[J]. 动态测试与分析,1988,21(2): 1-6.
刘峻华,黄树红. 汽轮机故障诊断技术的发展与展望[J]. 汽轮机技术,2000.2,40(1):1~6
史忠植. 高级人工智能[M]. 北京,科学出版社,1998
王永庆. 人工智能原理与方法[M]. 西安,西安交通大学出版社,1998.5
于文虎, 蒋瑞金, 倪维斗. 汽轮发电机组振动故障诊断专家系统的知识范围[J]. 中国电力,1996,29(10):24-29.
Saito K, Nakano R. Medical diagnostic expert system based on PDP models[J]. Proceedings of IEEE ICNN, San Diego, CA, July 24-27, 1988, 2:525-532
王士同. 模糊推理理论与模糊专家系统[M]. 北京,北京航空航天大学出版社, 1997.
A. J. Gonzalez, S. Lowenfeld. On-line Diagnosis of Turbine-Generators Using Artificial Intelligence [J]. IEEE Transaction on Energy Conversion, 1986, (2):150-161.
阮跃等. 汽轮机故障诊断专家系统的知识获取[J]. 中国电力, 1997, 30(2):11-13
张雪江,钟秉林,黄仁. 汽轮发电机组故障诊断专家系统知识处理技术的研究[J]. 振动工程学报,1996,9(3):230-236
焦李成. 神经网络系统理论[M]. 西安: 西安交通大学出版社, 1990.
赵振宇、徐用懋. 模糊理论和神经网络的基础与应用[M]. 北京: 清华大学出版社, 1995.
D.E.Rumelhart, J.L.McClelland. Parallel distributed processing explorations in the microstructures of cognition [M]. Fundations MIT Press, cambridge, MA, 1986.
J. J. Hopfield. Neural networks and physical systems with emergent collective computation abilities [J]. Prco.Natl. Acad. Sci, 1982: 2554~2558.
Part S K. Hopfield neural network for AR spectral estimation [C]. Inter. Sympo. on Circuits and Systems, USA, 1990; 487-490.
李化. 汽轮发电机组振动故障智能诊断模型的理论及方法研究[D]. 博士学位论文,重庆大学,1999.7.
J josephson, B Chandrasekaran, et al. A mechanism for forming composite explanatory hypotheses. IEEE Trans on Systems [J]. Man and Cybernetics, 1987.17(3): 445-454
G. E.Hinton, T. J. Sejnowski. Learning and relearning in Bolzman machine, Parallel Distributed Processing [M]: USA, MIT Press, 1986
Chen T, Chen H. Approximation to Nonlinear Continuous Functional by Neural Networks with Application to Dynamic Systems [J]. IEEE Trans on NN, 1993, 4:910-918
王宝和. 人工神经网络在汽轮发电机组故障诊断中的应用[J]. 数据采集与处理, 1995, 6(2): 146-151.
Pawlak Z. Rough sets [J]. International Journal of information and Computer Science, 1982, (11): 341-356.
Pawlak Z. Vagueness and uncertainty–a rough set perspective [J]. Computational Intelligence, 1995, 11(2):227 – 232.
曾黄麟. 粗糙集理论及其运用[M]. 重庆, 重庆大学出版社, 1998
王珏,苗夺谦,周育键. 关于理论与应用的综述[J]. 模式的识别与人工智能, 1996, 9(4): 337-344
Wygralak M. Rough sets and fuzzy sets-some remarks on interrelations [J]. Fuzzy sets and Sysrems, 1989, 29(3): 241 – 243.
Nanda S et al. Fuzzy rough sets [J]. Fuzzy sets and Systems, 1992, 45(2): 157~160
Golan R and Ziarko W. Methodology for stock market analysis utilizing rough set theory [C]. Proc. of IEEE/IAFE Conference on Computational Intelligence for Financial Engineering, New Jersey, 1995: 32~40.
Hu xiaohua, et al. Mining knowledge rules from databases – a rough set approach[C]. Proc. of IEEE International Conference on data Engineering, Los Alamitos, 1996, 96~105.
Arima M, et al. Fuzzy logic and rough sets controller for HVAC systems[C]. Proc. IEEE WESCANEX Communications, Power, and Computing, New York, 1995, 133~138.
Peng C et al. Multi-valued neural network and the knowledge acquisition method by the rough sets for recognition problem[C]. Proc .of the IEEE International Conference on Systems, Man and Cybemetics, Beijing, 1996, 736 – 740.
Jelonek J, et al. Rough set reduction of attributes ad their domains for neural networks [J]. Computational Intelligence, 1995,11(2): 339~347.
Yasdi R. Combining rough sets learning and neural learning method to deal with uncertain and imprecise information [J]. Neural computing, 1995,7(1): 61~84.
韩祯祥, 张琦, 文福拴. 粗糙集理论及其应用综述[J]. 控制理论与应用, 1998, 31(4): 32~38.
张琦, 韩祯祥, 文福拴. 一种基于粗糙集方法的电力系统故障诊断警报处理的新方法[J]. 中国电力, 1998, 31(4): 32~38.
张琦, 韩祯祥等. 用于暂态稳定评估的人工神经网络输入空间压缩方法[J]. 电力系统自动化, 2001, 1: 32~35.
邓聚龙. 灰色控制理论, 华中理工大学出版社 1985.
何耀华, 韩守木等. 汽轮发电机组故障诊断从模糊自动诊断到ANN应用[J]. 汽轮机技术, 1996, (8): 210-213.
何永勇, 张雪口等. 125MW汽轮发电机组状态实时监测与故障智能诊断系统的设计与实现. 中国电力, 1996, 3: 20-24.
Smiley, R.G. Rotating Machinery Monitoring and Fault Diagnosis. Sound Vibration, 15(9), Sept 1983.
李勇, 叶荣学等. 基于BP网络的凝汽器故障隶属函数及模糊诊断方法, 汽轮机技术, Vol., 37, 8(4), 1995: 199-203.
Davis L. Handbook of genetic algorithms [M]. Van Nostrand Reinhold, New York, 1991
Z.米凯利维茨著. 演化程序——遗传算法和数据编码的结合(中文版)[M]. 北京: 科学出版社, 2000.
玄光南. 遗传算法与工程设计(中文版)[M]. 北京: 科学出版社, 2000.
陈国良等编. 遗传算法及其应用[M]. 北京: 人民邮电出版社, 1996.
许仪勋, 陆拯等. 基于遗传算法的电力系统分层信息故障诊断方法[J]. 继电器, 2000, 28(10): 15-18.
周杨平,赵炳全. 利用遗传算法的核电厂故障诊断方法[J]. 清华大学学报(自然科学版). 1999.39(2):47-50.
文福拴,韩祯祥. 基于覆盖集理信论和Tabu搜索方法的电力系统警报处理[J]. 电力系统自动化. 1997.21(2):18-36.
文福拴,韩祯祥. 基于遗传算法和模拟退火算法的电力系统的故障诊断[J]. 中国电机工程学报. 1994.14(3):29-35.
De Jong, K. Genetic algorithms: 25 yer perspective [M]. IEEE Press, 1994.
Geotge D. Smith, Nigel C. Artificial neural nets and genetic algorithms[C]. Proceedings of the
international conference in Norwich, U. K. 1997:1920-1925.
李洪兴, 汪培庄. 模糊数学[M]. 北京: 国防工业出版社, 1994.
张涵孚, 何正嘉. 模糊诊断原理及应用[M]. 西安: 西安交通大学出版社, 1992.
韩捷, 张瑞林等. 旋转机械故障机理及诊断技术[M]. 北京: 机械工业出版社, 1997.
史植忠. 神经网络计算[M]. 北京: 电子工业出版社, 1993.
胡守仁. 神经网络应用技术[M]. 北京: 国防科技大学出版社, 1993.
代劲松, 宋素芳. 基于BP网络模型的汽轮发电机组的振动故障诊断[J]. 中国电力, 1996.29(6): 40-45.
刘占生, 夏松波. 人工神经网络在汽轮发电机组故障诊断中的应用[J]. 汽轮机技术, 1995.37(1): 8-20.
韩震宇, 朱鲁闯等. 大型回转机械故障诊断的神经网络分类器[J]. 成都科技大学学报, 1996.6: 18-27.
汪健, 蒋东翔等. 模糊自组织神经网络在汽轮机转子故障诊断中的应用. 热能动力工程, 1998.13(1): 43-45.
陈岳东, 屈梁生. 神经网络在大型回转机械故障诊断中的应用. 西安交通大学学报, 1992.8(4): 53-60.
师汉民, 陈吉红等. 人工神经网络及其在机械工程领域中的应用. 中国机械工程, 1997.8(2): 5-10.
苑希民, 李鸿雁等. 神经网络和遗传算法在水科学领域的应用[M]. 中国水利出版社, 2002.
王士同编著. 神经模糊系统及其应用[M]. 北京: 北京航空航天大学出版社, 1998.
阎平凡,张长水编著. 神经网络与模拟进化计算[M]. 北京: 清华大学出版社, 2000.
Song-Yee Yoon, Soo-Young Lee. Training alogorithm with incomplete data for feed forward neural networks [J]. Neural processing letters, 1999(10): 171 – 179.
Richard Hahnloser. Learning algorithms based on linearization network [J]. Compute neural system, 1998(9): 363 – 380.
P.M.Wong, T.D.Gedon. A pattern adaptive technique to handle data quality varation [J]. Neural processing letters, 1999(10): 7 – 15.
Roman Rosipal, Milos Koska, Igor Farkas. Prediction of chaotic time-series with a resource- allocating RBF network [J]. Neural processing letters, 1998(7): 185 – 197
Teuvo Kohonen. Fast evolutionary learning with batch-type self-organizing maps [J]. Neural processing letters, 1999 (9): 153 – 162.
Julio Ortega, Ignacio Rojas, Antonio F. Diaz, Alberto. Parallel coarse grain computing of Boltzman machines [J]. Neural processing letters, 1998(7): 169 – 184.
Yutaka Fukuoka, Hideo Matsuki, Hasruyuki Minamitani, Akimasa Ishida. A modified back-propagation method to avoid false local minima [J]. Neural networks, 1998 (11): 1059 – 1072.
Amit gupta, Siuwa M.Lam. Weight decay backpropagation for noisy data. Neural networks, 1998 (11): 1127 – 1137.
Bernhand Sendhoff, Martin Kreutz. A Model for the dynamic interaction between evolution and learning [J]. Neural processing letters, 1999(10): 181 – 193.
Xiaoxiao TANG, JieGU Li. Determination of topology and weights of the feed forward ANN by genetic evolution[C]. SPIE, 1997, 30 – 77.
Michard k. Belew and Michael D. Sreele and Rudolf F.Albrecht. Artificial neural nets and genetic algorithms [C]. Proceedings of the international conference in Norwich, U. K., 1997:650-653.
Holland J. Genetic algorithms and classifier systems: foundations and future directions, Genetic algorithms and their applications [C]. Proceedings of the second international conference on genetic algorithms, Beijing, china, 1997:626-630
李士勇. 模糊控制、神经控制和智能控制论[M]. 哈尔滨: 哈尔滨工业大学出版社, 1996.
A.S.Pandya, D.R.Kulkarnt, J.C.Parikh. Study of time series prediction under noisy environment [J]. Applications and science of artificial neural networks, 1997(Ⅲ): 21 – 24.
Benyang Tang, Willian Hshied, Fred Tanggang. “Clearing” neural network with continuity constraint for prediction of noisy time series[C]. ICONIP Hong Kong, 1996:143-146
许飞云, 贾民平等. 旋转机械振动故障诊断的一种模糊神经网络方法研究[J]. 振动工程学报, 1996, 9(3): 213-218.
项新建. 基于粗糙集理论的电力变压器故障诊断研究[J]. 仪器仪表学报, 2003,24(6): 568-572
常梨云, 王国胤, 吴渝. 一种基于Rough Set理论的属性约简及规则提取方法[J]. 软件学报, 1999, 10(11): 1206-～1211.
孙颖楷, 张邦礼, 曹龙汉等. 基于粗糙集理论的人工神经网络故障诊断系统[J]. 重庆大学学报, 2000, 23(6): 53-55.
史忠植. 知识发现[M]. 北京: 清华大学出版社, 2002.
贾要勤, 徐光华. 粗糙集属性约简的基因算法[J]. 中国机械工程, 2000,11(7): 777-801.
Zhang Q, Han Z X and WEN F S. A new approach for fault diagnosis in power systems based on rough set theory[C]. APSCOM’97, Hong Kong, 1997, 597 – 602.
Nurmi H et al. Probabilistic, fuzzy and rough concepts in social choice [J]. European Journal of Operational Reasearch, 1996,95(2): 264 – 277.
Pawlak Z et al. Rough sets [J]. Communications of ACM, 1995, 38(11): 89-95.
Banerjee M and Pal S K. Roughness of a fuzzy set [J]. Information Sciences, 1996, 93(3,4): 235 – 246.
Tsumoto Sh et al. Extraction of domain knowledge from based on rough set theory [C]. IEEE International Conference on Fuzzy Systems, New Jersey, 1996,748 – 754
Sienkiewicz J. Rough set and rough function approaches to the control algorithm reconstruction [D]. Institute of Computer Scince Reports, Warsaw University of Technology Warsaw, 1996
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): 103-108.
Mrozek A et al. methodology of rough controller synthesis [J]. Proceeding of IEEE International Conference on Fuzzy Systems, New JERSEY, 1996,1135 – 1139
Pawlak Z. Rough sets, rough relations and rough function fundamental Information [J]. 1996, 27(2,3): 103 –108.
Plonka L and Mrozek A. Rule-Based stabilization of the inverted pendulum [J]. Computational Intelligence, 1995, 11(2): 348 – 356.
Czogala E et al. Idea of a rough fuzzy controller and application to the stabilization of a pendulum-car system [J]. Fuzzy Sets and system, 1995, 72, (1): 61 – 73.
Skowton A et al. From rough set theory to evidence theory-Advances in the Dempster Shafer Theory of Evidence [M]. New York: John Wiley & sons Inc., 1994, 193 – 236.
黄德双. 神经网络模式识别系统理论[M]. 北京: 电子工业出版社, 1996.
杨建刚, 戴德成等. 改进BP网络在旋转机械故障诊断中的应用[J]. 振动工程学报, 1995, 8(4):342-350.
张文修, 梁怡等. 遗传算法的数学基础[J]. 西安: 西安交通大学出版社, 2000.
陈长征, 徐玉秀等. 遗传算法改进及其在机械故障诊断中的应用研究[J]. 机械科学与技术, 2000,19(3): 392-394.
王文辉, 周东华. 基于遗传算法的一种粗糙集知识约简算法[J]. 系统仿真学报, 2002(8): 91-94.
张彼德. 汽轮发电机组振动多故障诊断模型及方法研究[D]. 博士学位论文, 重庆大学, 2002
段玉倩, 贺家李. 遗传算法及其改进[J]. 电力系统及其自动化学报, 1998, 10(1): 39-51.
余涛, 王晶, 高峰, 束洪春. 水电机组故障诊断的集成知识表示与推理[J]. 中国电机工程学报, 2000,20(4): 68-71
戈志华, 宋之平, 李如翔, 田松峰. 基于热参数的汽轮发电机组多故障诊断模型[J].
热能动力工程,,2002,15(88): 420-422
张文修, 梁怡等. 遗传算法的数学基础[J]. 西安. 西安交通大学出版社. 2000
Harold H. Szu Brian Telfer, Shubha Kadambe. Neural Network Adaptive Wavelets for Signal Representation and Classification. Opt Eng. 1992.31(5): 1907-1916.
Vignaux G A, et al. A genetic algorithm for the linear transportation problem [J]. IEEE Trans. On Systems, Man and Cybernetics. 1991.21(2): 445-452
Verlysn M J, John V C. Building a composite syntax for expert system shell [J]. IEEE EXPERT, 1997, 25(6): 61-65
Patick C, John M. Application of neural networks to expert systems and command and control systems [J], 1987,16(4): 118～125.
杨建刚等.集成旋转机械故障诊断的知识表示与推理[J]. 东南大学学报, 1995, 25(3).
杨建刚,戴德成等. 改进BP网络在旋转机械故障诊断中的应用[J]. 振动工程学报. 1995. 8(4):342-350
余 涛, 王晶, 高峰, 束洪春. 水电机组故障诊断的集成知识表示与推理[J]. 中国电机工程学报, 2000,20(4): 68-71
李伟清. 汽轮发电机故障检查分析与预防[M]. 北京:中国电力出版社,1996.
杨叔子,郑晓军. 人工智能与诊断专家系统[M]. 西安:西安交通大学出版社,1990:1~59。
高毅龙. 数据挖掘及其在工程诊断中的应用[D]. 博士学位论文,西安交通大学,2002.4.
史进渊,张兆鹤等. 大型汽轮机研究的某些新进展[J]. 动力工程,1999,19(2):1~7.
李录平,韩西京等. 火电机组故障诊断技术的现状与展望[J]. 电力情报,1997,3:1~3.
施维新. 汽轮发电机组振动[M]. 北京:水利电力出版社,1990.
郭桂蓉,谢维信. 模糊模式识别[M]. 北京:国防科技大学出版社,1993
J.S.米切尔. 机械故障的分析与诊断[M]. 北京:机械工业出版社,1990.
倪维斗,蒋东翔. 大型电站性能监测分析与诊断技术研究[J]. 动力工程,1997,17(3):1~5.
徐敏. 机械故障诊断技术的发展动向与问题[J]. 动态测试与分析,1988,21(2): 1-6.
刘峻华,黄树红. 汽轮机故障诊断技术的发展与展望[J]. 汽轮机技术,2000.2,40(1):1~6
史忠植. 高级人工智能[M]. 北京,科学出版社,1998
王永庆. 人工智能原理与方法[M]. 西安,西安交通大学出版社,1998.5
于文虎, 蒋瑞金, 倪维斗. 汽轮发电机组振动故障诊断专家系统的知识范围[J]. 中国电力,1996,29(10):24-29.
Saito K, Nakano R. Medical diagnostic expert system based on PDP models[J]. Proceedings of IEEE ICNN, San Diego, CA, July 24-27, 1988, 2:525-532
王士同. 模糊推理理论与模糊专家系统[M]. 北京,北京航空航天大学出版社, 1997.
A. J. Gonzalez, S. Lowenfeld. On-line Diagnosis of Turbine-Generators Using Artificial Intelligence [J]. IEEE Transaction on Energy Conversion, 1986, (2):150-161.
阮跃等. 汽轮机故障诊断专家系统的知识获取[J]. 中国电力, 1997, 30(2):11-13
张雪江,钟秉林,黄仁. 汽轮发电机组故障诊断专家系统知识处理技术的研究[J]. 振动工程学报,1996,9(3):230-236
焦李成. 神经网络系统理论[M]. 西安: 西安交通大学出版社, 1990.
赵振宇、徐用懋. 模糊理论和神经网络的基础与应用[M]. 北京: 清华大学出版社, 1995.
D.E.Rumelhart, J.L.McClelland. Parallel distributed processing explorations in the microstructures of cognition [M]. Fundations MIT Press, cambridge, MA, 1986.
J. J. Hopfield. Neural networks and physical systems with emergent collective computation abilities [J]. Prco.Natl. Acad. Sci, 1982: 2554~2558.
Part S K. Hopfield neural network for AR spectral estimation [C]. Inter. Sympo. on Circuits and Systems, USA, 1990; 487-490.
李化. 汽轮发电机组振动故障智能诊断模型的理论及方法研究[D]. 博士学位论文,重庆大学,1999.7.
J josephson, B Chandrasekaran, et al. A mechanism for forming composite explanatory hypotheses. IEEE Trans on Systems [J]. Man and Cybernetics, 1987.17(3): 445-454
G. E.Hinton, T. J. Sejnowski. Learning and relearning in Bolzman machine, Parallel Distributed Processing [M]: USA, MIT Press, 1986
Chen T, Chen H. Approximation to Nonlinear Continuous Functional by Neural Networks with Application to Dynamic Systems [J]. IEEE Trans on NN, 1993, 4:910-918
王宝和. 人工神经网络在汽轮发电机组故障诊断中的应用[J]. 数据采集与处理, 1995, 6(2): 146-151.
Pawlak Z. Rough sets [J]. International Journal of information and Computer Science, 1982, (11): 341-356.
Pawlak Z. Vagueness and uncertainty–a rough set perspective [J]. Computational Intelligence, 1995, 11(2):227 – 232.
曾黄麟. 粗糙集理论及其运用[M]. 重庆, 重庆大学出版社, 1998
王珏,苗夺谦,周育键. 关于理论与应用的综述[J]. 模式的识别与人工智能, 1996, 9(4): 337-344
Wygralak M. Rough sets and fuzzy sets-some remarks on interrelations [J]. Fuzzy sets and Sysrems, 1989, 29(3): 241 – 243.
Nanda S et al. Fuzzy rough sets [J]. Fuzzy sets and Systems, 1992, 45(2): 157~160
Golan R and Ziarko W. Methodology for stock market analysis utilizing rough set theory [C]. Proc. of IEEE/IAFE Conference on Computational Intelligence for Financial Engineering, New Jersey, 1995: 32~40.
Hu xiaohua, et al. Mining knowledge rules from databases – a rough set approach[C]. Proc. of IEEE International Conference on data Engineering, Los Alamitos, 1996, 96~105.
Arima M, et al. Fuzzy logic and rough sets controller for HVAC systems[C]. Proc. IEEE WESCANEX Communications, Power, and Computing, New York, 1995, 133~138.
Peng C et al. Multi-valued neural network and the knowledge acquisition method by the rough sets for recognition problem[C]. Proc .of the IEEE International Conference on Systems, Man and Cybemetics, Beijing, 1996, 736 – 740.
Jelonek J, et al. Rough set reduction of attributes ad their domains for neural networks [J]. Computational Intelligence, 1995,11(2): 339~347.
Yasdi R. Combining rough sets learning and neural learning method to deal with uncertain and imprecise information [J]. Neural computing, 1995,7(1): 61~84.
韩祯祥, 张琦, 文福拴. 粗糙集理论及其应用综述[J]. 控制理论与应用, 1998, 31(4): 32~38.
张琦, 韩祯祥, 文福拴. 一种基于粗糙集方法的电力系统故障诊断警报处理的新方法[J]. 中国电力, 1998, 31(4): 32~38.
张琦, 韩祯祥等. 用于暂态稳定评估的人工神经网络输入空间压缩方法[J]. 电力系统自动化, 2001, 1: 32~35.
邓聚龙. 灰色控制理论, 华中理工大学出版社 1985.
何耀华, 韩守木等. 汽轮发电机组故障诊断从模糊自动诊断到ANN应用[J]. 汽轮机技术, 1996, (8): 210-213.
何永勇, 张雪口等. 125MW汽轮发电机组状态实时监测与故障智能诊断系统的设计与实现. 中国电力, 1996, 3: 20-24.
Smiley, R.G. Rotating Machinery Monitoring and Fault Diagnosis. Sound Vibration, 15(9), Sept 1983.
李勇, 叶荣学等. 基于BP网络的凝汽器故障隶属函数及模糊诊断方法, 汽轮机技术, Vol., 37, 8(4), 1995: 199-203.
Davis L. Handbook of genetic algorithms [M]. Van Nostrand Reinhold, New York, 1991
Z.米凯利维茨著. 演化程序——遗传算法和数据编码的结合(中文版)[M]. 北京: 科学出版社, 2000.
玄光南. 遗传算法与工程设计(中文版)[M]. 北京: 科学出版社, 2000.
陈国良等编. 遗传算法及其应用[M]. 北京: 人民邮电出版社, 1996.
许仪勋, 陆拯等. 基于遗传算法的电力系统分层信息故障诊断方法[J]. 继电器, 2000, 28(10): 15-18.
周杨平,赵炳全. 利用遗传算法的核电厂故障诊断方法[J]. 清华大学学报(自然科学版). 1999.39(2):47-50.
文福拴,韩祯祥. 基于覆盖集理信论和Tabu搜索方法的电力系统警报处理[J]. 电力系统自动化. 1997.21(2):18-36.
文福拴,韩祯祥. 基于遗传算法和模拟退火算法的电力系统的故障诊断[J]. 中国电机工程学报. 1994.14(3):29-35.
De Jong, K. Genetic algorithms: 25 yer perspective [M]. IEEE Press, 1994.
Geotge D. Smith, Nigel C. Artificial neural nets and genetic algorithms[C]. Proceedings of the
international conference in Norwich, U. K. 1997:1920-1925.
李洪兴, 汪培庄. 模糊数学[M]. 北京: 国防工业出版社, 1994.
张涵孚, 何正嘉. 模糊诊断原理及应用[M]. 西安: 西安交通大学出版社, 1992.
韩捷, 张瑞林等. 旋转机械故障机理及诊断技术[M]. 北京: 机械工业出版社, 1997.
史植忠. 神经网络计算[M]. 北京: 电子工业出版社, 1993.
胡守仁. 神经网络应用技术[M]. 北京: 国防科技大学出版社, 1993.
代劲松, 宋素芳. 基于BP网络模型的汽轮发电机组的振动故障诊断[J]. 中国电力, 1996.29(6): 40-45.
刘占生, 夏松波. 人工神经网络在汽轮发电机组故障诊断中的应用[J]. 汽轮机技术, 1995.37(1): 8-20.
韩震宇, 朱鲁闯等. 大型回转机械故障诊断的神经网络分类器[J]. 成都科技大学学报, 1996.6: 18-27.
汪健, 蒋东翔等. 模糊自组织神经网络在汽轮机转子故障诊断中的应用. 热能动力工程, 1998.13(1): 43-45.
陈岳东, 屈梁生. 神经网络在大型回转机械故障诊断中的应用. 西安交通大学学报, 1992.8(4): 53-60.
师汉民, 陈吉红等. 人工神经网络及其在机械工程领域中的应用. 中国机械工程, 1997.8(2): 5-10.
苑希民, 李鸿雁等. 神经网络和遗传算法在水科学领域的应用[M]. 中国水利出版社, 2002.
王士同编著. 神经模糊系统及其应用[M]. 北京: 北京航空航天大学出版社, 1998.
阎平凡,张长水编著. 神经网络与模拟进化计算[M]. 北京: 清华大学出版社, 2000.
Song-Yee Yoon, Soo-Young Lee. Training alogorithm with incomplete data for feed forward neural networks [J]. Neural processing letters, 1999(10): 171 – 179.
Richard Hahnloser. Learning algorithms based on linearization network [J]. Compute neural system, 1998(9): 363 – 380.
P.M.Wong, T.D.Gedon. A pattern adaptive technique to handle data quality varation [J]. Neural processing letters, 1999(10): 7 – 15.
Roman Rosipal, Milos Koska, Igor Farkas. Prediction of chaotic time-series with a resource- allocating RBF network [J]. Neural processing letters, 1998(7): 185 – 197
Teuvo Kohonen. Fast evolutionary learning with batch-type self-organizing maps [J]. Neural processing letters, 1999 (9): 153 – 162.
Julio Ortega, Ignacio Rojas, Antonio F. Diaz, Alberto. Parallel coarse grain computing of Boltzman machines [J]. Neural processing letters, 1998(7): 169 – 184.
Yutaka Fukuoka, Hideo Matsuki, Hasruyuki Minamitani, Akimasa Ishida. A modified back-propagation method to avoid false local minima [J]. Neural networks, 1998 (11): 1059 – 1072.
Amit gupta, Siuwa M.Lam. Weight decay backpropagation for noisy data. Neural networks, 1998 (11): 1127 – 1137.
Bernhand Sendhoff, Martin Kreutz. A Model for the dynamic interaction between evolution and learning [J]. Neural processing letters, 1999(10): 181 – 193.
Xiaoxiao TANG, JieGU Li. Determination of topology and weights of the feed forward ANN by genetic evolution[C]. SPIE, 1997, 30 – 77.
Michard k. Belew and Michael D. Sreele and Rudolf F.Albrecht. Artificial neural nets and genetic algorithms [C]. Proceedings of the international conference in Norwich, U. K., 1997:650-653.
Holland J. Genetic algorithms and classifier systems: foundations and future directions, Genetic algorithms and their applications [C]. Proceedings of the second international conference on genetic algorithms, Beijing, china, 1997:626-630
李士勇. 模糊控制、神经控制和智能控制论[M]. 哈尔滨: 哈尔滨工业大学出版社, 1996.
A.S.Pandya, D.R.Kulkarnt, J.C.Parikh. Study of time series prediction under noisy environment [J]. Applications and science of artificial neural networks, 1997(Ⅲ): 21 – 24.
Benyang Tang, Willian Hshied, Fred Tanggang. “Clearing” neural network with continuity constraint for prediction of noisy time series[C]. ICONIP Hong Kong, 1996:143-146
许飞云, 贾民平等. 旋转机械振动故障诊断的一种模糊神经网络方法研究[J]. 振动工程学报, 1996, 9(3): 213-218.
项新建. 基于粗糙集理论的电力变压器故障诊断研究[J]. 仪器仪表学报, 2003,24(6): 568-572
常梨云, 王国胤, 吴渝. 一种基于Rough Set理论的属性约简及规则提取方法[J]. 软件学报, 1999, 10(11): 1206-～1211.
孙颖楷, 张邦礼, 曹龙汉等. 基于粗糙集理论的人工神经网络故障诊断系统[J]. 重庆大学学报, 2000, 23(6): 53-55.
史忠植. 知识发现[M]. 北京: 清华大学出版社, 2002.
贾要勤, 徐光华. 粗糙集属性约简的基因算法[J]. 中国机械工程, 2000,11(7): 777-801.
Zhang Q, Han Z X and WEN F S. A new approach for fault diagnosis in power systems based on rough set theory[C]. APSCOM’97, Hong Kong, 1997, 597 – 602.
Nurmi H et al. Probabilistic, fuzzy and rough concepts in social choice [J]. European Journal of Operational Reasearch, 1996,95(2): 264 – 277.
Pawlak Z et al. Rough sets [J]. Communications of ACM, 1995, 38(11): 89-95.
Banerjee M and Pal S K. Roughness of a fuzzy set [J]. Information Sciences, 1996, 93(3,4): 235 – 246.
Tsumoto Sh et al. Extraction of domain knowledge from based on rough set theory [C]. IEEE International Conference on Fuzzy Systems, New Jersey, 1996,748 – 754
Sienkiewicz J. Rough set and rough function approaches to the control algorithm reconstruction [D]. Institute of Computer Scince Reports, Warsaw University of Technology Warsaw, 1996
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): 103-108.
Mrozek A et al. methodology of rough controller synthesis [J]. Proceeding of IEEE International Conference on Fuzzy Systems, New JERSEY, 1996,1135 – 1139
Pawlak Z. Rough sets, rough relations and rough function fundamental Information [J]. 1996, 27(2,3): 103 –108.
Plonka L and Mrozek A. Rule-Based stabilization of the inverted pendulum [J]. Computational Intelligence, 1995, 11(2): 348 – 356.
Czogala E et al. Idea of a rough fuzzy controller and application to the stabilization of a pendulum-car system [J]. Fuzzy Sets and system, 1995, 72, (1): 61 – 73.
Skowton A et al. From rough set theory to evidence theory-Advances in the Dempster Shafer Theory of Evidence [M]. New York: John Wiley & sons Inc., 1994, 193 – 236.
黄德双. 神经网络模式识别系统理论[M]. 北京: 电子工业出版社, 1996.
杨建刚, 戴德成等. 改进BP网络在旋转机械故障诊断中的应用[J]. 振动工程学报, 1995, 8(4):342-350.
张文修, 梁怡等. 遗传算法的数学基础[J]. 西安: 西安交通大学出版社, 2000.
陈长征, 徐玉秀等. 遗传算法改进及其在机械故障诊断中的应用研究[J]. 机械科学与技术, 2000,19(3): 392-394.
王文辉, 周东华. 基于遗传算法的一种粗糙集知识约简算法[J]. 系统仿真学报, 2002(8): 91-94.
张彼德. 汽轮发电机组振动多故障诊断模型及方法研究[D]. 博士学位论文, 重庆大学, 2002
段玉倩, 贺家李. 遗传算法及其改进[J]. 电力系统及其自动化学报, 1998, 10(1): 39-51.
余涛, 王晶, 高峰, 束洪春. 水电机组故障诊断的集成知识表示与推理[J]. 中国电机工程学报, 2000,20(4): 68-71
戈志华, 宋之平, 李如翔, 田松峰. 基于热参数的汽轮发电机组多故障诊断模型[J].
热能动力工程,,2002,15(88): 420-422
张文修, 梁怡等. 遗传算法的数学基础[J]. 西安. 西安交通大学出版社. 2000
Harold H. Szu Brian Telfer, Shubha Kadambe. Neural Network Adaptive Wavelets for Signal Representation and Classification. Opt Eng. 1992.31(5): 1907-1916.
Vignaux G A, et al. A genetic algorithm for the linear transportation problem [J]. IEEE Trans. On Systems, Man and Cybernetics. 1991.21(2): 445-452
Verlysn M J, John V C. Building a composite syntax for expert system shell [J]. IEEE EXPERT, 1997, 25(6): 61-65
Patick C, John M. Application of neural networks to expert systems and command and control systems [J], 1987,16(4): 118～125.
杨建刚等.集成旋转机械故障诊断的知识表示与推理[J]. 东南大学学报, 1995, 25(3).
杨建刚,戴德成等. 改进BP网络在旋转机械故障诊断中的应用[J]. 振动工程学报. 1995. 8(4):342-350
余 涛, 王晶, 高峰, 束洪春. 水电机组故障诊断的集成知识表示与推理[J]. 中国电机工程学报, 2000,20(4): 68-71