转子故障信号的量化特征提取方法研究
|
摘要
故障诊断技术主要包括三部分的研究内容,即信号处理、特征提取、故障辨识。特征提取,是对系统的动态信号预处理后得到的信息进行分析,提取与系统状态有关的数据,再分析这些数据,提取其中与系统状态相关性较大的敏感特征,是故障诊断技术的关键,理论研究的热点之一。特征提取的完善和正确与否,直接影响到诊断是否成功和诊断结果的准确性。常用的信号特征提取方法存在以下两点不足：(1)难以准确描述系统非线性及信号的非平稳信号特征；(2)难以解决信号特征的定量评价问题。本文采用信息熵分析方法,对机械信号特征提取和定量评价方法进行研究。
针对转子实验台的数据模型,运用信息熵方法对故障类别、程度分别给出客观的量化评价方法。主要工作内容及获得的研究结论如下：
1)在认真查阅国内外大量文献的基础上,分析信息熵测度在故障诊断中的研究现状和存在的问题。对信息熵的性质和时域的奇异谱熵、频域的功率谱熵和时-频域的小波能谱熵进行了较为系统的研究和探讨。
2)以轴承-转子系统动力学模型为基础,研究了它的常见的故障的机理。设计了有限冲激响应低通滤波器,对采集的信号进行滤波,为特征提取提供原始数据。同时把基于AR模型最大熵法的功率谱算法应用到故障类别的诊断中,分辨率比传统的方法高,谱线平滑,同时抗噪的能力很强,很适合轴承-转子的数据处理。
3)研究了盲信号处理的Fast-ICA算法和AMUSE算法,通过实例仿真分析可得,由于Fast-ICA算法的分离性能指标较小和自身的优点,所以选择Fast-ICA算法分离后的数据作为奇异谱熵的样本数据。提出了基于Fast-ICA的奇异谱熵算法。通过对实验信号的分析表明,该算法能有效评价转子振动状态的特征指标。
4)基于信息融合思想,对描述振动信号能量的三种信息熵测度,即时域的奇异谱熵、频域的功率谱熵、时频域的小波能谱熵,在根据广义集合概念对上述三种信息熵测度进行特征级的信息融合基础上,提出了一种基于时空(场)广义信息熵集合的轴承-转子系统故障辨识方法。分析表明,该方法拥有在三维特征空间图形化描述故障状态域、使不同故障类别间显示出显著差别的性能,它对提高辨识故障的准确率具有参考价值。
信息熵理论在故障诊断领域带来了研究热潮,在特征的量化提取方面值得进一步深入地研究。
Fault diagnosis consists of three parts of the content, that is, signal processing, feature extraction, fault identification.Feature extraction, is a dynamic signal preprocessing system analysis of the information obtained by extraction with the system state of the data, then analyze these data, extract the system state-dependent with greater sensitivity Feature, is the key of fault diagnosis and one of the focuses of theoretical research.Whether feather is extracted completely and correctly or not, directly affects the success of diagnosis and diagnostic accuracy. Signal feature extraction method commonly used the following two shortcomings:(1)Difficult to accurately describe the nonlinear and non stationary signal characteristics;(2)Difficult to solve the signal characteristics of the quantitative evaluation.In this paper, I use entropy analysis method to study the mechanical signal feature extraction and quantitative evaluation methods.
Rotor test bed for the data model,using information entropy for the fault type, degree are given an objective quantitative evaluation.Main contents and conclusions of the study were as follows:
1))Based on searching a lot of domestic and foreign literature current situation and existing problems of information entropy measure in fault diagnosis are analyzed.The nature of information entropy and spectral entropy of the singular time domain, frequency domain power spectral entropy and time-frequency domain of wavelet energy spectrum entropy are studied and disscussed systematically.
2))Its common failure mechanism is studied based on bearing-Rotor System Dynamics model.A finite impulse response low-pass filter is designed,which filters the collected signals,to provide raw data for the feature extraction.While the AR model based on maximum entropy method of power spectrum algorithm is applied to fault diagnosis categories,which has higher resolution than traditional methods,smooth spectrum,strong ability of noise immunity,and fits bearing-Rotor data processing very much.
3)Fast-ICA and AMUSE algorithms which are dealed with the blind signal are studied.Based on the simulation analysis,the data separated from Fast-ICA algorithm is selected as singular spectrum entropy of the sample data because of smaller separation performance Its own merits.Singular spectrum entropy algorithm based on Fast-ICA algorithm is proposed.Through the analysis of experimental signals,the algorithm can effectively evaluate the state of rotor vibration characteristics of indicators.
4) In the view of information fusion,application methods of three kinds of information entropy measures,which describe vibration signal energy, such as the singular spectrum entropy in the time domain, power spectrum entropy in the frequency domain and wavelet energy spectrum entropy in the time-frequency domain, In accordance with Generalized sets concept by the feature information fusion about the above-mentioned three kinds of information entropy measures,a new fault identification method in the bearing-rotor system which base on Generalized sets concept of time spatial of the information entropy is proposed.The analysis shows that the method has the Function of three-dimensional feature space graphical representation of fault state domain, demonstrates significant differences between different fault types,and enhances the accuracy of identification fault with a reference value.
Entropy theory in the field of fault diagnosis of fever brought in the quantitative extraction of features worthy of further study.
针对转子实验台的数据模型,运用信息熵方法对故障类别、程度分别给出客观的量化评价方法。主要工作内容及获得的研究结论如下：
1)在认真查阅国内外大量文献的基础上,分析信息熵测度在故障诊断中的研究现状和存在的问题。对信息熵的性质和时域的奇异谱熵、频域的功率谱熵和时-频域的小波能谱熵进行了较为系统的研究和探讨。
2)以轴承-转子系统动力学模型为基础,研究了它的常见的故障的机理。设计了有限冲激响应低通滤波器,对采集的信号进行滤波,为特征提取提供原始数据。同时把基于AR模型最大熵法的功率谱算法应用到故障类别的诊断中,分辨率比传统的方法高,谱线平滑,同时抗噪的能力很强,很适合轴承-转子的数据处理。
3)研究了盲信号处理的Fast-ICA算法和AMUSE算法,通过实例仿真分析可得,由于Fast-ICA算法的分离性能指标较小和自身的优点,所以选择Fast-ICA算法分离后的数据作为奇异谱熵的样本数据。提出了基于Fast-ICA的奇异谱熵算法。通过对实验信号的分析表明,该算法能有效评价转子振动状态的特征指标。
4)基于信息融合思想,对描述振动信号能量的三种信息熵测度,即时域的奇异谱熵、频域的功率谱熵、时频域的小波能谱熵,在根据广义集合概念对上述三种信息熵测度进行特征级的信息融合基础上,提出了一种基于时空(场)广义信息熵集合的轴承-转子系统故障辨识方法。分析表明,该方法拥有在三维特征空间图形化描述故障状态域、使不同故障类别间显示出显著差别的性能,它对提高辨识故障的准确率具有参考价值。
信息熵理论在故障诊断领域带来了研究热潮,在特征的量化提取方面值得进一步深入地研究。
Fault diagnosis consists of three parts of the content, that is, signal processing, feature extraction, fault identification.Feature extraction, is a dynamic signal preprocessing system analysis of the information obtained by extraction with the system state of the data, then analyze these data, extract the system state-dependent with greater sensitivity Feature, is the key of fault diagnosis and one of the focuses of theoretical research.Whether feather is extracted completely and correctly or not, directly affects the success of diagnosis and diagnostic accuracy. Signal feature extraction method commonly used the following two shortcomings:(1)Difficult to accurately describe the nonlinear and non stationary signal characteristics;(2)Difficult to solve the signal characteristics of the quantitative evaluation.In this paper, I use entropy analysis method to study the mechanical signal feature extraction and quantitative evaluation methods.
Rotor test bed for the data model,using information entropy for the fault type, degree are given an objective quantitative evaluation.Main contents and conclusions of the study were as follows:
1))Based on searching a lot of domestic and foreign literature current situation and existing problems of information entropy measure in fault diagnosis are analyzed.The nature of information entropy and spectral entropy of the singular time domain, frequency domain power spectral entropy and time-frequency domain of wavelet energy spectrum entropy are studied and disscussed systematically.
2))Its common failure mechanism is studied based on bearing-Rotor System Dynamics model.A finite impulse response low-pass filter is designed,which filters the collected signals,to provide raw data for the feature extraction.While the AR model based on maximum entropy method of power spectrum algorithm is applied to fault diagnosis categories,which has higher resolution than traditional methods,smooth spectrum,strong ability of noise immunity,and fits bearing-Rotor data processing very much.
3)Fast-ICA and AMUSE algorithms which are dealed with the blind signal are studied.Based on the simulation analysis,the data separated from Fast-ICA algorithm is selected as singular spectrum entropy of the sample data because of smaller separation performance Its own merits.Singular spectrum entropy algorithm based on Fast-ICA algorithm is proposed.Through the analysis of experimental signals,the algorithm can effectively evaluate the state of rotor vibration characteristics of indicators.
4) In the view of information fusion,application methods of three kinds of information entropy measures,which describe vibration signal energy, such as the singular spectrum entropy in the time domain, power spectrum entropy in the frequency domain and wavelet energy spectrum entropy in the time-frequency domain, In accordance with Generalized sets concept by the feature information fusion about the above-mentioned three kinds of information entropy measures,a new fault identification method in the bearing-rotor system which base on Generalized sets concept of time spatial of the information entropy is proposed.The analysis shows that the method has the Function of three-dimensional feature space graphical representation of fault state domain, demonstrates significant differences between different fault types,and enhances the accuracy of identification fault with a reference value.
Entropy theory in the field of fault diagnosis of fever brought in the quantitative extraction of features worthy of further study.
引文
[1]钟秉林,黄仁.机械故障诊断学[M].北京：机械工业出版社,2003.
[2]李国华,张永忠.机械故障诊断[M].北京：化学工业出版社,1999.
[3]陶魄.中厚钢板轧机扭矩监测的应用研究[J].机械设计与制造工程,2002,31(1)：72-74.
[4]徐敏.设备故障诊断手册——机械设备状态检测和故障诊断[M].西安：西安交通大学出版社,1998：120-122.
[5]肖正华.国内外设备诊断技术发展概况[J].电力情报,1997,(4)：120-124.
[6]杨叔子.设备诊断技术的现状与未来[J].设备管理与维修,1995,(1)：50-55.
[7]C.E.Shannon.A Mathematical Theory of Communication [J].The Bell System Technical Journal,1984,(27):379-423,623-656.
[8]邢修三.熵产生率公式及其应用[J].物理学报,2003,52(12)：2969-2977.
[9]邢修三.物理熵、信息熵及其演化方程[J].中国科学(A辑),2001,31(1)：78-86.
[10]田玉楚.非线性动态系统的宏观信息熵分析[J].通信学报,1997,18(1)：47-53.
[11]E.T.Jaynes.Information Theory and Statistical Mechanics.Phys Rev,1957,106 (4):620-630.
[12]A.N.Kolmogorov. Three Approaches to the Quantitative Definition of Information.Problems of Information Transmission,1965,1(1):1-7.
[13]G.J.Chaitin.Information-Theoretic Computational Complexiy. IEEE Trans Inform,Theory,1974,IT-20:10-15.
[14]S.M.Pincus.APPrxoimate Entropy as a Measure of System Complexity. Proc. Natl.Acad.Sci,1991,88:2297-2301.
[15]S.S.Dragomir. An Inequality for Logarithmic Mapping and Applications for the Shannon Entropy. Computers and Mathematics with Applications,2003,46(8): 1273-1279.
[16]D.Erdogmus,J.C.Principe.Information Transfer throuh Classifiers and Its Relation to Probability of Error. Proceedings.IJCNN'01,2001,Florida:50-54.
[17]J.Trebicki,K.Sobczyk.Maximum Entropy Principle and Non-stationary Distributions of Stochastic Systems.Probabilistic Engineering Mechanics, 2004,11(3):169-178.
[18]S.Aviyente,W.J.Williams.Minimum Entropy Time-Frequency Distributions. Signal Processing Lettesr,2005,(5):37-40.
[19]J.Hagenauer,Z.Dawy. Genomic Analysis using Methods from Information Theory. Information Theory Workshop,IEEE,2004,24:55-59.
[20]M.G. de Bruin,C.Kamminga. The effect of signal nomraliaztioning on enrtopy sums.PattenrrecongitionLetters,1998,(19):415-23.
[21]S Mark. Roulston.Estimating the errors on measured entropy and mutual inofrmation.Physieal D,1999:28-5294.
[22]Bienvenu Fassinut Mombot,Jean-Bernard Choquel.A new probabistic entropy fusion approach for management of information sources.Inofrmation Fusion,2004,(5),35-47.
[23]K Robert. Niven. The constrained entropy and cross-enrtopy functions. Physical,2003,(5):256-263.
[24]S.M.Pincus.Approximate enrtopy as a measure of system complexity. Proc.Natl.Acad.Sci,1991:2297-2301.
[25]M.PinCus.A Regularity Statistic for Medical Data Analysis.Journal of clinical Monitoring,1991,7(4):335-345.
[26]杨福生,廖旺才.近似熵：一种适用于短数据的复杂性度量[J].中国医疗器械杂志,1997,21(5)：83-286.
[27]胥永刚,李凌均.近似嫡及其在机械设备故障诊断中的应用[J].信息与控制,2002,31(6)：547-551.
[28]胥永刚,何正嘉.基于二维近似熵度量轴心轨迹复杂性的研究[J].西安交通大学学报,2003,37(11)：1171-1174.
[29]林京,屈梁生.信号时频熵及其在齿轮裂纹识别中的应用[J].机械传动,1998,22(2)：37-39.
[30]何正友,钱清泉.多分辨信息熵的计算及在故障检测中的应用[J].电力自动化设备,2001,21(5)：9-11.
[31]杨文献,姜节胜.机械信号奇异熵研究[J].机械工程学报,2000,36(12)：122-126.
[32]谢平,刘彬,林洪彬.多分辨率奇异谱熵及其在振动信号监测中的应用研究[J].传感技术学报,2004,17(4)：547-550.
[33]申弢,黄树红,韩守木,等.旋转机械振动信号的信息熵特征[J].机械工程学报,2001,37(06)：94-98.
[34]陈非,黄树红,张燕平等.基于信息熵距的旋转机械振动故障诊断方法[J].振动、测试与诊断,2008,28(01)：9-13.
[35]周萌清.信息理论基础[M].北京：北京航空航天大学,2002.
[36]周伟.MATLAB小波分析高级技术[M].西安：西安电子科技大学出版,2005.
[37]李力.机械信号处理及其应用[M].武汉：华中科技大学出版社,2007.
[38]胡广书.数字信号处理——理论、算法与实现[M].北京：清华大学出版社,2003.
[39]师汉民.机械振动系统——分析·测试·建模·对策[M].武汉：华中科技大学出版社,2003
[40]杨国安.机械设备故障诊断实用技术[M].北京：中国石化出版社,2007.
[41]陈大禧,朱铁光.大型回转机械诊断现场实用技术[M].北京：机械工业出版社,2002.
[42]李正周.MATLAB数字信号处理与应用[M].北京：清华大学出版社,2008.
[43]苏宏艳,梁华庆.提高线性调频连续波探地雷达厚度检测分辨率的信号处理方法[D].西安交通大学,2006.
[44]吴道虎.基于声学的水轮机状态监测技术研究[D].华中科技大学,2006.
[45]桂中华.水轮机故障智能诊断及振动数字化预测研究[D].华南理工大学,2005.
[46]DONG Xiaomei,XIANG Guang,YU Ge LI Xiaohua. A new A New Detection Approach Based on the Maximum Entropy Model [J].Wuhan University Journal of Natural Science.2006,11(6):1765-1768.
[47]淦玲莉,徐加,张飞.基于最大熵法的汽车毫米波雷达信号的处理[J].探测与控制学报,2006,28(5)：65-68.
[48]王宇,迟毅林,伍星,等.基于盲信号处理的机械噪声监测与故障诊断[J].振动与冲击,2009,28(6)：32-41.
[49]王明祥.独立分量分析方法及在图像处理中的应用研究[D].上海交通大学,2005.
[50]侯进勇.独立分量分析及其在信号处理中的应用研究[D].南京信息工程大学,2009.
[51]谢亮.基于独立分量分析特征提取方法的研究及其应用[D].浙江师范大学,2009.
[52]孙俊平,刘扬.基于快速独立分量分析的多分辨率遥感图像融合算法[J].中国电子科学研究院学报,2007,2(3)：228-233.
[53]A.Hyvarinen and E. Oja. A Fast Fixed-Point Algorithm for Independent Component Analysis.Neural Computation,1997,9(7):1483-1492.
[54]A.Hyvarinen.Fast and Robust Fixed-Point Algorithms for Independent Component Analysis. IEEE Transactions on Neural Networks, 1999,10(3):626-634.
[55]A.Hyvarinen and E.Oja. Independent Component Analysis:Algorithms and Applications.Neural Networks,2000,13(4-5):411-430.
[56]李焱骏,王厚军,师奕兵.AMUSE算法在声波测井数据处理中的应用[J].四川大学学报,2009,41(6)：242-246.
[57]L.Tong, V. Soon, Y. F. Huang, and R.Liu.Indeterminacy and identifiability of blind identification.IEEE Trans.CAS.1991,38,499-509.
[58]蔡兴国,马平.基于信息融合技术的并发故障诊断的研究[J].中国电机工程学报,2003,23(5)：112-116.
[59]Qiang Fu,Yi Shen,Jian Qiu Zhang,Shengli Liu. An approach to fault diagnosis based on a hierarchical information fusion scheme[and turbine application]. Instrumentation and Measurement Technology Conference,2001.IMTC 2001.Proceedings of the 18th IEEE,2001,2(5):875-878.
[60]王清印,赵秀恒,王峰丽.广义集合概念及其内涵剖析[J].模糊系统与数学,2006,20(4)：61-67.
[61]袁小宏,屈梁生.机械故障诊断中的信息融合利用问题研究[J].振动、测试与诊断,1999,3(19)：187-192.
[62]赵荣珍,李朝辉,张白桦等.基于灰关联信息融合的转子系统早期故障发现研究[J].兰州理工大学学报,2006,32(1)：37-41.
[63]张学文.组成论[M].合肥：中国科学技术大学出版社,2003.
[2]李国华,张永忠.机械故障诊断[M].北京：化学工业出版社,1999.
[3]陶魄.中厚钢板轧机扭矩监测的应用研究[J].机械设计与制造工程,2002,31(1)：72-74.
[4]徐敏.设备故障诊断手册——机械设备状态检测和故障诊断[M].西安：西安交通大学出版社,1998：120-122.
[5]肖正华.国内外设备诊断技术发展概况[J].电力情报,1997,(4)：120-124.
[6]杨叔子.设备诊断技术的现状与未来[J].设备管理与维修,1995,(1)：50-55.
[7]C.E.Shannon.A Mathematical Theory of Communication [J].The Bell System Technical Journal,1984,(27):379-423,623-656.
[8]邢修三.熵产生率公式及其应用[J].物理学报,2003,52(12)：2969-2977.
[9]邢修三.物理熵、信息熵及其演化方程[J].中国科学(A辑),2001,31(1)：78-86.
[10]田玉楚.非线性动态系统的宏观信息熵分析[J].通信学报,1997,18(1)：47-53.
[11]E.T.Jaynes.Information Theory and Statistical Mechanics.Phys Rev,1957,106 (4):620-630.
[12]A.N.Kolmogorov. Three Approaches to the Quantitative Definition of Information.Problems of Information Transmission,1965,1(1):1-7.
[13]G.J.Chaitin.Information-Theoretic Computational Complexiy. IEEE Trans Inform,Theory,1974,IT-20:10-15.
[14]S.M.Pincus.APPrxoimate Entropy as a Measure of System Complexity. Proc. Natl.Acad.Sci,1991,88:2297-2301.
[15]S.S.Dragomir. An Inequality for Logarithmic Mapping and Applications for the Shannon Entropy. Computers and Mathematics with Applications,2003,46(8): 1273-1279.
[16]D.Erdogmus,J.C.Principe.Information Transfer throuh Classifiers and Its Relation to Probability of Error. Proceedings.IJCNN'01,2001,Florida:50-54.
[17]J.Trebicki,K.Sobczyk.Maximum Entropy Principle and Non-stationary Distributions of Stochastic Systems.Probabilistic Engineering Mechanics, 2004,11(3):169-178.
[18]S.Aviyente,W.J.Williams.Minimum Entropy Time-Frequency Distributions. Signal Processing Lettesr,2005,(5):37-40.
[19]J.Hagenauer,Z.Dawy. Genomic Analysis using Methods from Information Theory. Information Theory Workshop,IEEE,2004,24:55-59.
[20]M.G. de Bruin,C.Kamminga. The effect of signal nomraliaztioning on enrtopy sums.PattenrrecongitionLetters,1998,(19):415-23.
[21]S Mark. Roulston.Estimating the errors on measured entropy and mutual inofrmation.Physieal D,1999:28-5294.
[22]Bienvenu Fassinut Mombot,Jean-Bernard Choquel.A new probabistic entropy fusion approach for management of information sources.Inofrmation Fusion,2004,(5),35-47.
[23]K Robert. Niven. The constrained entropy and cross-enrtopy functions. Physical,2003,(5):256-263.
[24]S.M.Pincus.Approximate enrtopy as a measure of system complexity. Proc.Natl.Acad.Sci,1991:2297-2301.
[25]M.PinCus.A Regularity Statistic for Medical Data Analysis.Journal of clinical Monitoring,1991,7(4):335-345.
[26]杨福生,廖旺才.近似熵：一种适用于短数据的复杂性度量[J].中国医疗器械杂志,1997,21(5)：83-286.
[27]胥永刚,李凌均.近似嫡及其在机械设备故障诊断中的应用[J].信息与控制,2002,31(6)：547-551.
[28]胥永刚,何正嘉.基于二维近似熵度量轴心轨迹复杂性的研究[J].西安交通大学学报,2003,37(11)：1171-1174.
[29]林京,屈梁生.信号时频熵及其在齿轮裂纹识别中的应用[J].机械传动,1998,22(2)：37-39.
[30]何正友,钱清泉.多分辨信息熵的计算及在故障检测中的应用[J].电力自动化设备,2001,21(5)：9-11.
[31]杨文献,姜节胜.机械信号奇异熵研究[J].机械工程学报,2000,36(12)：122-126.
[32]谢平,刘彬,林洪彬.多分辨率奇异谱熵及其在振动信号监测中的应用研究[J].传感技术学报,2004,17(4)：547-550.
[33]申弢,黄树红,韩守木,等.旋转机械振动信号的信息熵特征[J].机械工程学报,2001,37(06)：94-98.
[34]陈非,黄树红,张燕平等.基于信息熵距的旋转机械振动故障诊断方法[J].振动、测试与诊断,2008,28(01)：9-13.
[35]周萌清.信息理论基础[M].北京：北京航空航天大学,2002.
[36]周伟.MATLAB小波分析高级技术[M].西安：西安电子科技大学出版,2005.
[37]李力.机械信号处理及其应用[M].武汉：华中科技大学出版社,2007.
[38]胡广书.数字信号处理——理论、算法与实现[M].北京：清华大学出版社,2003.
[39]师汉民.机械振动系统——分析·测试·建模·对策[M].武汉：华中科技大学出版社,2003
[40]杨国安.机械设备故障诊断实用技术[M].北京：中国石化出版社,2007.
[41]陈大禧,朱铁光.大型回转机械诊断现场实用技术[M].北京：机械工业出版社,2002.
[42]李正周.MATLAB数字信号处理与应用[M].北京：清华大学出版社,2008.
[43]苏宏艳,梁华庆.提高线性调频连续波探地雷达厚度检测分辨率的信号处理方法[D].西安交通大学,2006.
[44]吴道虎.基于声学的水轮机状态监测技术研究[D].华中科技大学,2006.
[45]桂中华.水轮机故障智能诊断及振动数字化预测研究[D].华南理工大学,2005.
[46]DONG Xiaomei,XIANG Guang,YU Ge LI Xiaohua. A new A New Detection Approach Based on the Maximum Entropy Model [J].Wuhan University Journal of Natural Science.2006,11(6):1765-1768.
[47]淦玲莉,徐加,张飞.基于最大熵法的汽车毫米波雷达信号的处理[J].探测与控制学报,2006,28(5)：65-68.
[48]王宇,迟毅林,伍星,等.基于盲信号处理的机械噪声监测与故障诊断[J].振动与冲击,2009,28(6)：32-41.
[49]王明祥.独立分量分析方法及在图像处理中的应用研究[D].上海交通大学,2005.
[50]侯进勇.独立分量分析及其在信号处理中的应用研究[D].南京信息工程大学,2009.
[51]谢亮.基于独立分量分析特征提取方法的研究及其应用[D].浙江师范大学,2009.
[52]孙俊平,刘扬.基于快速独立分量分析的多分辨率遥感图像融合算法[J].中国电子科学研究院学报,2007,2(3)：228-233.
[53]A.Hyvarinen and E. Oja. A Fast Fixed-Point Algorithm for Independent Component Analysis.Neural Computation,1997,9(7):1483-1492.
[54]A.Hyvarinen.Fast and Robust Fixed-Point Algorithms for Independent Component Analysis. IEEE Transactions on Neural Networks, 1999,10(3):626-634.
[55]A.Hyvarinen and E.Oja. Independent Component Analysis:Algorithms and Applications.Neural Networks,2000,13(4-5):411-430.
[56]李焱骏,王厚军,师奕兵.AMUSE算法在声波测井数据处理中的应用[J].四川大学学报,2009,41(6)：242-246.
[57]L.Tong, V. Soon, Y. F. Huang, and R.Liu.Indeterminacy and identifiability of blind identification.IEEE Trans.CAS.1991,38,499-509.
[58]蔡兴国,马平.基于信息融合技术的并发故障诊断的研究[J].中国电机工程学报,2003,23(5)：112-116.
[59]Qiang Fu,Yi Shen,Jian Qiu Zhang,Shengli Liu. An approach to fault diagnosis based on a hierarchical information fusion scheme[and turbine application]. Instrumentation and Measurement Technology Conference,2001.IMTC 2001.Proceedings of the 18th IEEE,2001,2(5):875-878.
[60]王清印,赵秀恒,王峰丽.广义集合概念及其内涵剖析[J].模糊系统与数学,2006,20(4)：61-67.
[61]袁小宏,屈梁生.机械故障诊断中的信息融合利用问题研究[J].振动、测试与诊断,1999,3(19)：187-192.
[62]赵荣珍,李朝辉,张白桦等.基于灰关联信息融合的转子系统早期故障发现研究[J].兰州理工大学学报,2006,32(1)：37-41.
[63]张学文.组成论[M].合肥：中国科学技术大学出版社,2003.