基于盲信号分离的齿轮系统故障诊断研究
|
摘要
齿轮系统作为现代工业系统中必不可少的机械传动装置,具有传递动力大,传递运动准确,传动平稳等诸多优点。随着现代机械设备向着大型化、高效率、高强度、自动化及高性能方向发展,作为传递运动和动力的齿轮装置发挥着越来越重要的作用。然而,由于其自身结构复杂,工作环境恶劣等原因,齿轮及齿轮箱都容易受到损害和出现故障。因此,采用先进的技术对齿轮及齿轮箱进行状态监测与故障诊断,可实现由事后维修、定期检修到视情维修的根本转变,减少不必要的损失,从而创造更大的经济效益和社会效益,具有重大的意义。
本文针对齿轮箱常见故障,分析其典型故障机理及振动特性,重点研究了两种故障特征提取技术,包括基于重构吸引子轨迹矩阵的改进奇异值分解技术和基于改进奇异值分解技术与盲信号分离相结合的故障诊断新技术,并将这两种方法用于实测故障信号的分析中,其结果为齿轮系统故障诊断提供了新的思路。
本文的主要研究内容及结论如下：
(1)改进了现有奇异值分解技术。第二章在详细研究基于重构吸引子轨迹矩阵的奇异值分解技术基本原理的基础上,引入自相关分析,改进了原有算法,使其更加科学合理。数值仿真试验及实测数据分析表明：改进后的奇异值分解技术能够成功地提取强噪声背景下的调制故障信息,对齿轮系统故障诊断具有重要意义。
(2)研究了盲信号分离的基本原理及应用。第三章详细推导了以JADE法为代表的批处理方法、以Infomax为代表的自适应算法及以FastICA为代表的固定点算法,并分析各自特点。数值仿真试验表明：以JADE法及FastICA法为代表的盲信号分离技术在多路混合信号中进行源分离是很有效的,这为齿轮系统故障诊断提供了新的思路。
(3)进行齿轮箱故障诊断实验。第四章根据现有实验条件,设计了实验方案,对原有齿轮箱故障实验台进行改进,设置典型故障类型进行了相关故障诊断实验。
(4)提出基于改进的奇异值分解技术与盲信号分离相结合的故障诊断新方法。第五章首先利用奇异值分解技术对实测信号降噪处理,再利用盲信号分离技术对降噪后信号进行盲源分离,通过奇异值分解技术与盲信号分离技术相结合,成功地分离出实测信号中的典型故障信号,其故障特征与实验设置故障完全吻合。同时,本实验数据的分离结果表明：JADE法与FastICA算法都能取得很好的分离效果。
最后,第六章对本文所取得的研究成果进行了总结,并指出了若干值得进一步研究的方向。
The gear system, which is considered as the necessary mechanical transmission equipment in modern industry, has many advantages such as large driving force, exact transferring motion, smooth transmission and so on. Gear system is becoming more and more important in transferring power and motion along with the development of large-scale, high efficiency and high strength equipments. However, the gears and gear boxes would be damaged and become failure easily because of its complex structure and bad running conditions. Accordingly, it is significant to research on condition monitoring and fault diagnosis for gear system by advanced technologies, which could not only change the current postmortem servicing and regular examining to repairing according to the specific state, but also bring more economical and social benefit.
This thesis is focused on the typical fault mechanism and vibration characteristic of gear system. It is mainly including two fault feature extracting techniques, one of which is the improved algorithm of the singularity value decomposition (SVD) about track matrix of attractor reconstructed by time series, and the other is the new method of using both the SVD algorithm and the blind signal separation (BSS) algorithm. Both the methods mentioned above are used in extracting the fault features, which could provide a new thought for faults diagnosis of the gear system.
The main research contents and the key conclusions are shown as follows:
(1)The existing singularity value decomposition (SVD) algorithm is improved in the second chapter. After studying the fundamental of the SVD about track matrix of attractor reconstructed by time series, the autocorrelation analysis is introduced, which improved the current algorithm and made it more logical. The analysis of the simulation signals and the measured signals from gear box shows that it is successful for the improved SVD algorithm in extracting modulated signals mixed by strong noises, which is significant to the gear system fault diagnosis.
(2)The third chapter is mainly on the fundamental and application of the BSS algorithm. Firstly, the batch-processing algorithm such as JADE, the self-adaptive algorithm such as Infomax and the fixed-point algorithm FastICA are researched in detail. And their characteristics are also researched. The simulation shows that both the JADE algorithm and the FastICA algorithm are effective in separating source signals from multi-signals, which provides a new way for the gear system fault diagnosis.
(3)The experiment for gear box faults diagnosis is carrying out in the fourth chapter. According to the laboratorial condition, some works are done, including designing the experimentation, improving the former gear box faults diagnosis platform, and carrying out the experiment with different diagnosis styles.
(4)The fifth chapter is focused on a new diagnosis technology based on both SVD and BSS. The signal-to-noise-ratio (SNR) of the measured signal is enhanced by the SVD algorithm at first. Then the signals after processing are separated by the BSS algorithm. The separation of typical diagnosis signals is quite successful by using the new method. The characteristic of the separated signals is quite accordant with the setting faults. At the same time, the separated results show that both the SVD algorithm and the BSS algorithm can do well in processing measured signals.
At last, the main results of this dissertation are summarized in the last chapter, and some possible valuable research directions are also pointed out.
本文针对齿轮箱常见故障,分析其典型故障机理及振动特性,重点研究了两种故障特征提取技术,包括基于重构吸引子轨迹矩阵的改进奇异值分解技术和基于改进奇异值分解技术与盲信号分离相结合的故障诊断新技术,并将这两种方法用于实测故障信号的分析中,其结果为齿轮系统故障诊断提供了新的思路。
本文的主要研究内容及结论如下：
(1)改进了现有奇异值分解技术。第二章在详细研究基于重构吸引子轨迹矩阵的奇异值分解技术基本原理的基础上,引入自相关分析,改进了原有算法,使其更加科学合理。数值仿真试验及实测数据分析表明：改进后的奇异值分解技术能够成功地提取强噪声背景下的调制故障信息,对齿轮系统故障诊断具有重要意义。
(2)研究了盲信号分离的基本原理及应用。第三章详细推导了以JADE法为代表的批处理方法、以Infomax为代表的自适应算法及以FastICA为代表的固定点算法,并分析各自特点。数值仿真试验表明：以JADE法及FastICA法为代表的盲信号分离技术在多路混合信号中进行源分离是很有效的,这为齿轮系统故障诊断提供了新的思路。
(3)进行齿轮箱故障诊断实验。第四章根据现有实验条件,设计了实验方案,对原有齿轮箱故障实验台进行改进,设置典型故障类型进行了相关故障诊断实验。
(4)提出基于改进的奇异值分解技术与盲信号分离相结合的故障诊断新方法。第五章首先利用奇异值分解技术对实测信号降噪处理,再利用盲信号分离技术对降噪后信号进行盲源分离,通过奇异值分解技术与盲信号分离技术相结合,成功地分离出实测信号中的典型故障信号,其故障特征与实验设置故障完全吻合。同时,本实验数据的分离结果表明：JADE法与FastICA算法都能取得很好的分离效果。
最后,第六章对本文所取得的研究成果进行了总结,并指出了若干值得进一步研究的方向。
The gear system, which is considered as the necessary mechanical transmission equipment in modern industry, has many advantages such as large driving force, exact transferring motion, smooth transmission and so on. Gear system is becoming more and more important in transferring power and motion along with the development of large-scale, high efficiency and high strength equipments. However, the gears and gear boxes would be damaged and become failure easily because of its complex structure and bad running conditions. Accordingly, it is significant to research on condition monitoring and fault diagnosis for gear system by advanced technologies, which could not only change the current postmortem servicing and regular examining to repairing according to the specific state, but also bring more economical and social benefit.
This thesis is focused on the typical fault mechanism and vibration characteristic of gear system. It is mainly including two fault feature extracting techniques, one of which is the improved algorithm of the singularity value decomposition (SVD) about track matrix of attractor reconstructed by time series, and the other is the new method of using both the SVD algorithm and the blind signal separation (BSS) algorithm. Both the methods mentioned above are used in extracting the fault features, which could provide a new thought for faults diagnosis of the gear system.
The main research contents and the key conclusions are shown as follows:
(1)The existing singularity value decomposition (SVD) algorithm is improved in the second chapter. After studying the fundamental of the SVD about track matrix of attractor reconstructed by time series, the autocorrelation analysis is introduced, which improved the current algorithm and made it more logical. The analysis of the simulation signals and the measured signals from gear box shows that it is successful for the improved SVD algorithm in extracting modulated signals mixed by strong noises, which is significant to the gear system fault diagnosis.
(2)The third chapter is mainly on the fundamental and application of the BSS algorithm. Firstly, the batch-processing algorithm such as JADE, the self-adaptive algorithm such as Infomax and the fixed-point algorithm FastICA are researched in detail. And their characteristics are also researched. The simulation shows that both the JADE algorithm and the FastICA algorithm are effective in separating source signals from multi-signals, which provides a new way for the gear system fault diagnosis.
(3)The experiment for gear box faults diagnosis is carrying out in the fourth chapter. According to the laboratorial condition, some works are done, including designing the experimentation, improving the former gear box faults diagnosis platform, and carrying out the experiment with different diagnosis styles.
(4)The fifth chapter is focused on a new diagnosis technology based on both SVD and BSS. The signal-to-noise-ratio (SNR) of the measured signal is enhanced by the SVD algorithm at first. Then the signals after processing are separated by the BSS algorithm. The separation of typical diagnosis signals is quite successful by using the new method. The characteristic of the separated signals is quite accordant with the setting faults. At the same time, the separated results show that both the SVD algorithm and the BSS algorithm can do well in processing measured signals.
At last, the main results of this dissertation are summarized in the last chapter, and some possible valuable research directions are also pointed out.
引文
[1]丰田利夫.设备现场诊断的开展方法[M].李敏,译.北京：机械工业出版社,1985.
[2]李润方,王建军.齿轮系统动力学-振动、冲击、噪声[M].北京：科学出版社,1997.
[3]李明,孙涛,胡海岩.齿轮传动转子-轴承系统动力学的研究进展[J].振动工程学报,2002,15(3)：249-256.
[4]张贤达,保铮.盲信号分离[J].电子学报,2001,29(12)：1766-1771.
[5]Optiz H. Noise of Gears[A]. In:Philosophical Transactions of the Royal Society of London, Series A, Mathematical and Physical Sciences[C]. The Royal Society:1968.369-380.
[6]Randall R B. A New Method of Modelling Gear Faults[J]. ASME Journal of Mechanical Design,1982,104:259-267.
[7]Platt J C,Cristianini N, Shawe-Taylor J. Large Margin DAGs for Multiclass Classification [J]. Advance in Neural Information Processing Systems 12,2000, NIP5-99:547-553.
[8]黄文虎,夏松波.设备故障原理、技术及应用[M].北京：科学技术出版社,1996.
[9]杜社亮,张云.频谱分析法在齿轮故障诊断中的应用研究[J].机电工程,1999,5(2)：211-213.
[10]李晓虎,贾民平,许飞云.频谱分析法在齿轮箱故障诊断中的应用[J].振动、测试与诊断,2003,23(3)：168-170.
[11]黄筱调,汪世益.旋转机械故障诊断的二次FFT分析法[J].机械科学与技术,2000,19(1)：97-99.
[12]牛立勇,关惠玲.细化和倒谱分析在坦克齿轮箱故障诊断中的应用[J].郑州大学学报(工学版),2003,24(3)：95-97.
[13]Sato T, Sasaki K. Bispectral Holography[J]. Journal of Acoustical Society of America,1977, 62(2):404-408.
[14]王华民,陈霞,安钢.基于高阶累积量的齿轮箱故障诊断研究[J].机械强度,2004,26(3)：247-249.
[15]郑海波,陈心昭,李志远.基于双谱的齿轮故障特征提取与识别[J].振动工程学报,2002,15(3)：354-358.
[16]张子瑜,陈进,史习智.双谱分析在齿轮故障诊断中的应用[J].振动工程学报,1998,11(5)：90-94.
[17]Mcfadden P D, Smith J D. Signal Processing Technique for Detecting Local Defects in A Gear from Signal Average of the Vibration[J]. Proceedings of the Institution of Mechanical Engineer,1985,199(4):287-292.
[18]Mcfadden P D. Examination of a Technique for the Early Detection of Failure in Gears by Signal Processing of the time Domain Average of the Meeshing Vibration[J]. Mechanical System and Signal Processing,1987,1(2):173-183.
[19]王延春,谢明,丁康.包络分析方法及其在齿轮故障振动诊断中的应用[J].重庆大学学报(自然科学版),1995,18(1)：87-91.
[20]皮钧,王建军.包络谱细化的新方法及在齿轮故障诊断中的应用[J].拖拉机与农用运输车,2003,5(2)：10-12.
[21]白士红,孙斌.包络方法诊断齿轮箱故障[J].沈阳航空工业学院学报,2000,17(4)：73-74.
[22]丁康,王延春.传动箱齿轮和轴故障的振动诊断方法的研究[J].振动与冲击,1994,13(2)：26-32.
[23]Forrester B D. Gear Fault Detection Using the Wigner-Ville Distribution[A]. Transactions of the Institution of Engineers[C], Australia:Mechanical Engineering,1990, ME16(1):73-77.
[24]Baydar N, Ball A. Detection of Gear Deterioration Under Varying Load Conditions by Using the Instantaneous Power Spectrum[J]. Mechanical Systems and Signal Processing,2000, 14(6):907-921.
[25]周凤星,程耕国,高立新.小波分析在大型齿轮箱故障诊断中的应用[J].武汉科技大学学报(自然科学版),2003,26(3)：282-284.
[26]郑海波,李志远,陈心昭.基于连续小波变换的齿轮故障诊断方法研究[J].机械工程学报,2002,28(3)：69-73.
[27]Wang W J, McFadden P D. Application of Orthogonal Wavelets to Early Gear Damage Detection[J]. Mechanical System and Signal Processing,1995,9(5):497-507.
[28]王妙云.利用小波分析早期发现齿轮故障隐患[J].中国设备工程,2004,7(2)：37-39.
[29]徐科,杨德斌,徐金梧.小波变换在齿轮局部缺陷诊断中的应用[J].机械工程学报,1999,35(3)：105-107.
[30]张立明.人工神经网络的模型及其应用[M].上海：复旦大学出版社,1993.
[31]Yang P, Yam L. Theoretical and Experimental Study on Fault Diagnosis of Gear box [J]. Integrating Dynamics Condition Monitoring and Control for the 21st Century,1999, 9(2):117-121.
[32]李凌均.统计学习理论在机械设备智能诊断中的应用研究[D].西安：西安交通大学机械工程学院,2003.
[33]Vladimir N. Vapnik著,张学工译.统计学习理论的本质[M].北京：清华大学出版社,2004.
[34]肖健华,樊可清,吴今培,等.应用于故障诊断的SVM理论研究[J].振动、测试与诊断,2001,21(4)：258-262.
[35]张周锁,李凌均,何正嘉.基于支持向量机的多故障分类器及应用[J].机械科学与技术,2004,23(5)：536-538.
[36]马祥华,沈水福,布昭元.齿轮故障诊断专家系统[J].北京科技大学学报,1994,16(5)：435-439.
[37]申永军,杨绍普,刘献栋.齿轮故障诊断中的信号处理技术研究与展望[J].机械传动,2004,28(3)：1-5.
[38]朱小勇.齿轮箱故障诊断研究与试验台的设计[D].重庆：重庆大学机械工程学院,2001.
[39]吕志民,张武军,徐金梧,等.基于奇异谱的降噪方法及其在故障诊断技术中的应用[J].机械工程学报,1999.35(3)：85-88.
[40]宋友.转子系统碰摩故障诊断及振动信号的降噪处理[D].北京：北京航空航天大学电子工程系,2002.
[41]Yang Wen-Xian, Peter W Tse. Development of an advanced noise reduction method for vibration analysis based on singular value decomposition[J]. NDT&E International,2003, 36(2):419-432.
[42]温广瑞,张西宁,屈梁生.奇异值分解技术在声音信息分离中的应用[J].西安交通大学学报,2003,37(1)：37-40.
[43]袁小宏,史东峰.奇异值分解技术在齿轮箱故障诊断中的应用[J].振动、测试与诊断,2000,20(2)：91-96.
[44]李建,刘红星,屈梁生.探测信号中周期性冲击分量的奇异值分解技术[J].振动工程学报,2002,15(4)：415-418.
[45]Kanjilal P P, Palit S,Saha G. Fetal ECG extraction from single channel maternal ECG using singular value decomposition[J]. IEEE Trans.on Biomedical Engineering,1997,44(1): 51-59.
[46]刘献栋,杨绍普,申永军,等.基于奇异值分解的突变信息检测新方法及其应用[J].机械工程学报,2002,38(6)：102-105.
[47]何田,刘献栋,李其汉.噪声背景下检测突变信息的奇异值分解技术[J].振动工程学报,2006,19(1)：399-403.
[48]Giannakis G B, Swami A. New results on state-space and input-output identification of non-Gaussian processing using cumulants[A]. In:Proc. SPIE'87, San Diego, CA,1987, 826:199-205.
[49]Linsker R. An application of the principle of maximum information preservation to linear systems[J]. Advances in Neural Information Processing Systems,1989,35(2),1-3.
[50]Linsker R. Self-organization in a perceptual network[J]. Computer,1988,21(2):105-117.
[51]Heralt J, Jutten C. Blind separation of sources, Part I:An adaptive algorithm based on neuromimatic architecture[J]. Signal Processing,1991,24(1):1-10.
[52]Sorouchyari E. Blind separation of sources, Part Ⅲ:Stability Analysis[J], Signal Processing, 1991,24(1):21-29.
[53]Comon P. Blind separation of sources, Part Ⅱ:Problem statement[J]. Signal Processing, 1991,24(1):11-20.
[54]Tong L, Li R W, Soon V C. Indeterminacy and identifiability of blind identification [J]. IEEE Trans. On Circuits and Systems,1991,38(5):499-509.
[55]Burel G. Blind separation of sources:A nonlinear neural algorithm[J]. Neural Network, 1992,5(2):937-947.
[56]Comon P. Independent component analysis, a new concept[J]. Signal Processing,1994, 36(2):287-314.
[57]Cichocki A, Unbehauen R, Moszczynski L, et al. Anew on-line adaptive learning algorithm for blind separation of source signals[A]. In:ISANN94[C]. Taiwan,1994:406-411.
[58]Oja E, Karhunen J, Wang L, et al. Principle and independent components in neural networks-Recent developments[A]. In:Proc.7th Italian Workshop Neural Network, WIRN'95[C]. Vietri, Italy,1995:20-26.
[59]Karhunen J, Joutsensalo J. Repressentation and separation of signals using nonlinear PCA type learning[J]. Neural Network,1994,7(2):113-127.
[60]Bell A J, Sejnowski T J. An information-maximization approach to blind separation and blind deconvolution[J]. Neural Computation,1995,7(6):1004-1034.
[61]Delfosse N, Loubaton P. Adaptive blind separation of independent sources:A deflation approach[J]. Signal Processing,1995,45(2):59-83.
[62]Matsuoka K. A neural net for blind separation of non-stationary signals[J]. Neural Network, 1995,3(2):311-419.
[63]Cardoso J F, Laheld B H. Equivariant adaptive source separation[J]. IEEE Trans. Signal Processing,1996,44(10):3017-3030.
[64]Pearlmuter B A, Parra L C. A context-sensitive-generalization of ICA[A]. In: Proc. Int. Conf. Neural Information Processing, ICONIP'96[C]. HongKong:1996,151-157.
[65]Cardoso J F. Infomax and maximum likelihood for source separation[J]. IEEE Signal Processing Letters,1997,4(2):109-111.
[66]Girolami M, Fyfe C. Kurtosis extrema and identification of independent components:a neural network approach[A]. In:Proc. ICASSP'97[C].1997,4:3329-3333.
[67]Pham D T, Garat P. Blind separation of mixture of independent sources through a quasi-maximum likelihood approach[J]. IEEE Tans. Signal Processing,1997,45(7): 1712-1725.
[68]Amari S-I, Cichoki A. Adaptive blind signal processing-neural network approaches [J]. Proceedings of the IEEE,1998,86(10):2026-2046.
[69]Cardoso J F. Blind signal separation:statistical principles[J]. Proceedings of the IEEE,1998, 86(10):2009-2025.
[70]Valpola H. Nonlinear independent component analysis using ensemble learning:Theory [A]. In:Proc. ICA2000[C]. Helsinki, Finland:2000,251-256.
[71]Valpola H, Giannakopoulos X, Honkela A, et al. Nonlinear independent component analysis using ensemble learning:Experiments and discussion[A]. In:Proc. ICA2000[C]. Helsinki, Finland:2000,351-356.
[72]Cho K S, Lee S Y. Implementation of Infomax ICA Algorithm with Analog CMOS Circuits [A]. In:Proc. ICA2001[C]. San Diego, CA, USA:2001,70-73.
[73]Cardoso J F, Delabrouille J, G Patanchon. Independent component analysis of the cosmic microware background[A]. In:Proc. ICA2003[C]. Nara, Japan:2003,1111-1116.
[74]Yuan Z, Oja E. A FastICA Algorithm for Non-negative Independent Component Analysis [A]. In:Proc. ICA2004[C]. Granada, Spain:2004,1-8.
[75]Bell A J, et al. An information-maximization approach to blind separation and deconvolution [J]. Neural Computation,1995,7(2):1129-1159.
[76]Lee T W, et al. Independent component analysis using an extended infomax algorithm for sub-Gaussian and super-Gaussian sources[J]. Neural Computation,1999,11(2):409-433.
[77]Amari S-I. New learning in structural parameter space-natural Riemannian gradient [J]. Advance in Neural Information Processing Systems,1997,9(2):127-133.
[78]Amari S-I. Natural gradient works efficiently in learning[J]. Neural Computation,1998, 10(2):251-276.
[79]Hyvarinen A, et al. A fast fixed-point algorithm for independent component analysis [J]. Neural Computation,1997,9(7),1483-1492.
[80]Hyvarinen A. Fast and robust fixed-point algorithm for independent component analysis [J]. IEEE Trans. On Neural Network,1999,10(3),626-634.
[81]Cardoso J F. Higher order contrast for independent component analysis[J]. Neural Computation,1999,11(1):157-193.
[82]Cardoso J F. Blind beam forming for non-Gaussian signal[J]. IEEE. Proc. F,1993,140(6): 362-370.
[83]张贤达.现代信号处理[M].(第2版).北京：清华大学出版社,2002.
[84]杨福生,洪波.独立分量分析的原理与应用[M].北京：清华大学出版社,2006.
[85]马仓建,刘奕龙,陈海洋.盲信号处理[M].北京：国防工业出版社,2006.
[86]刘琚,何振亚.盲源分离和盲反卷积[J].电子学报,2002,30(4)：570-576.
[87]Alexander Ypma, Amir Leshem, Robert P W Duin. Blind separation of rotating machine sources:bilinear forms and convolutive mixtures[J]. Neuro computing-Special Issue on ICA/BSS,2002,35(2):123-134.
[88]Gelle G, Colas M. Delaunay G. Blind sources separation applied to rotating machines monitoring by acoustical and vibrations analysis[J], Mechanical Systems and Signal Processing,2000,14(3):427-442.
[89]Roan M J, Erling J G, Sibul L H. A new non-linear adaptive blind source separation approach to gear tooth failure detection and analysis[J]. Mechanical Systems and Signal Processing, 2002.16(5):719-740.
[90]Shen Yongjun, Yang Shaopu. A New Blind Source Separation Method and its Application to Fault Diagnosis of Rolling Bearing[J]. International Journal of Nonlinear Science and Numerical Simulation,2006,7(3):245-250.
[91]吴军彪,陈进,伍星.基于盲源分离技术的故障特征信号分离方法[J].机械强度,2002,24(4)：485-488.
[92]钟振茂,陈进,钟平.盲源分离技术用于机械故障诊断的研究初探[J].机械科学与技术,2002,21(2)：282-284.
[93]李舜酩.机械振动信号盲源分离的时域方法[J].应用力学学报,2005.22(4)：579-584.
[94]焦卫东,杨世锡,吴昭同.基于独立分量分析的噪声消除技术研究[J].浙江大学学报(工学版),2004,38(7)：872-876.
[95]李加文,李从心.基于鲁棒预白化的机械噪声信号盲分离[J].机械科学与技术,2005,24(12)：1499-1501.
[96]宋友,柳重堪,李其汉.基于三阶累计量的转子振动信号降噪方法研究[J].航空动力学报,2002,17(3)：363-366.
[97]任海峰,胡小平,吴建军.应用独立分量分析提取液体火箭发动机的故障特征[J].推进技术,2004,25(6)：481-483.
[98]陈仲生,杨拥民,沈国际.独立分量分析在直升机齿轮箱故障早期诊断中的应用[J].机械科学与技术,2004,23(4)：481-483.
[99]郝志华,马孝江,王奉涛.非平稳信号的盲源分离在机械故障诊断中的应用[J].振动与冲击,2006,25(1)：110-114.
[100]陈进,钟平.复杂声场中的频谱分离[J].振动与冲击,2002,21(1)：54-56.
[101]秦国军,莫芙蓉.滚动轴承含噪声谐波信号的欠确定盲源分离方法研究[J].国防科技大学学报,2006,28(1)：103-106.
[102]季忠,金涛,杨炯明,等.基于独立分量分析的消噪方法在旋转机械特征提取中的应用[J].中国机械工程,2005,16(1)：50-53.
[103]张永祥,明延涛,王洪磊.基于最小互信息准则的盲源分离在齿轮箱故障诊断中的应用[J].机械设计与制造,2006,6(2)：87-89.
[104]宋晓萍,廖明夫.盲源分离方法在旋转机械故障诊断中的应用[J].机械设计与制造,2006,3(2)：88-90.
[105]吴军彪,陈进,钟平,等.机械噪声故障特征提取的盲分离法及小波提纯法[J].上海交通大学学报,2003,37(5)：766-769.
[106]黄闯,侍洪波.基于独立分量分析(ICA)与小波变换的过程监测方法[J].吉林大学学报(工学版),2004,34(3)：465-470.
[107]焦卫东.基于互信息的小波特征提取方法及其在机械故障诊断中的应用[J].中国机械工程,2004,15(21)：1946-1949
[108]陈国金,梁军,钱积新.基于小波变换消噪和盲源信号分离的过程监控方法[J].化工学报,2005,56(5)：885-889.
[109]葛楠,刘月辉.独立分量分析在内燃机噪声信号分离技术中的应用[J].天津大学学报,2006,39(4)：454-457.
[110]李熠,何永勇,李志农,等.盲源分离和小波变换在碰摩声频信号分析中的应用研究[J].机械强度,2005,27(6)：719-724.
[111]吴小培,冯焕清,周何琴,等.基于独立分量分析的混合声信号分离[J].中国科学技术大学学报,2001,31(1)：68-73.
[112]宋友,柳重堪,李其汉.含噪振动信号中早期碰摩的故障检测研究[J].航空学报,2003,24(1)：32-35.
[113]杨世锡,焦卫东,吴昭同.独立分量分析基网络应用于旋转机械故障特征提取与分类[J].机械工程学报,2004,40(3)：45-49.
[114]杨世锡,焦卫东,吴昭同.基于独立分量分析特征提取的复合神经网络故障诊断法[J].振动工程学报,2004,17(4)：438-442.
[115]焦卫东,杨世锡,吴昭同.机械故障模式识别的ICA基神经网络方法[J].农业机械学报,2004,35(4)：151-154.
[116]焦卫东,杨世锡,吴昭同.复合ICA-SVM机械状态模式分类[J].中国机械工程,2004,15(1)：62-65.
[117]Widodo, Achmad, Yang, et al. Combination of independent component analysis and support vector machines for intelligent faults diagnosis of induction motors[J]. Expert Systems with Applications,2007,32(2):299-312
[118]焦卫东,杨世锡,钱苏翔,等.乘性噪声消除的同态变换盲源分离算法[J].浙江大学学报(工学版),2006,40(4)：581-584.
[119]焦卫东,杨世锡,吴昭同.机械声源信号的带通滤波盲分离[J].振动工程学报,2003,16(3)：344-348.
[120]何宁,谢磊,郭明等.基于独立成份的动态多变量过程的故障检测与诊断方法[J].化工学报,2005,56(4)：646-652.
[121]屈微.刘贺平,张德政.基于独立分量分析特征提取的故障诊断系统[J].北京科技大学学报,2006,28(7)：700-703.
[122]李良敏.基于遗传算法的盲源分离在轴承诊断中的应用[J].轴承,2005,9(2)：31-34.
[123]郝志华,马孝江.局域波法和独立成份分析在转子系统故障诊断上的应用[J].中国电机工程学报,2005,25(3)：84-88.
[124]胡红英,马孝江.局域波近似熵及其在机械故障诊断中的应用[J].振动与冲击,2006,25(4)：38-41.
[125]何清波,孔凡让,朱忠奎,等.盲卷积分离及其在机械振动信号消噪中的应用研究[J].振动与冲击,2006,25(2)：30-34.
[126]Cover T M, Thomas J A. Elements of information theory[M]. New York:John Wiley and Sons, LTD,1991.
[127]Hyvarinen A, Karhunen J, Oja E. Independent component analysis[M]. New York:John Wiley and Sons, LTD,2001,166.
[128]Cichocki A, Thawonmas R, Amari S. Sequential blind signal extraction in order specified by stochastic properties[J]. Electronics Letters,1997,33(1):64-65.
[129]Hyvarinen A, Oja E. Independent component analysis:algorithms and applications [J]. Neural Networks,2000,13(2):411-430.
[130]焦卫东.基于独立分量分析的旋转机械故障诊断方法研究[D].杭州：浙江大学机械与能源工程学院,2003.
[2]李润方,王建军.齿轮系统动力学-振动、冲击、噪声[M].北京：科学出版社,1997.
[3]李明,孙涛,胡海岩.齿轮传动转子-轴承系统动力学的研究进展[J].振动工程学报,2002,15(3)：249-256.
[4]张贤达,保铮.盲信号分离[J].电子学报,2001,29(12)：1766-1771.
[5]Optiz H. Noise of Gears[A]. In:Philosophical Transactions of the Royal Society of London, Series A, Mathematical and Physical Sciences[C]. The Royal Society:1968.369-380.
[6]Randall R B. A New Method of Modelling Gear Faults[J]. ASME Journal of Mechanical Design,1982,104:259-267.
[7]Platt J C,Cristianini N, Shawe-Taylor J. Large Margin DAGs for Multiclass Classification [J]. Advance in Neural Information Processing Systems 12,2000, NIP5-99:547-553.
[8]黄文虎,夏松波.设备故障原理、技术及应用[M].北京：科学技术出版社,1996.
[9]杜社亮,张云.频谱分析法在齿轮故障诊断中的应用研究[J].机电工程,1999,5(2)：211-213.
[10]李晓虎,贾民平,许飞云.频谱分析法在齿轮箱故障诊断中的应用[J].振动、测试与诊断,2003,23(3)：168-170.
[11]黄筱调,汪世益.旋转机械故障诊断的二次FFT分析法[J].机械科学与技术,2000,19(1)：97-99.
[12]牛立勇,关惠玲.细化和倒谱分析在坦克齿轮箱故障诊断中的应用[J].郑州大学学报(工学版),2003,24(3)：95-97.
[13]Sato T, Sasaki K. Bispectral Holography[J]. Journal of Acoustical Society of America,1977, 62(2):404-408.
[14]王华民,陈霞,安钢.基于高阶累积量的齿轮箱故障诊断研究[J].机械强度,2004,26(3)：247-249.
[15]郑海波,陈心昭,李志远.基于双谱的齿轮故障特征提取与识别[J].振动工程学报,2002,15(3)：354-358.
[16]张子瑜,陈进,史习智.双谱分析在齿轮故障诊断中的应用[J].振动工程学报,1998,11(5)：90-94.
[17]Mcfadden P D, Smith J D. Signal Processing Technique for Detecting Local Defects in A Gear from Signal Average of the Vibration[J]. Proceedings of the Institution of Mechanical Engineer,1985,199(4):287-292.
[18]Mcfadden P D. Examination of a Technique for the Early Detection of Failure in Gears by Signal Processing of the time Domain Average of the Meeshing Vibration[J]. Mechanical System and Signal Processing,1987,1(2):173-183.
[19]王延春,谢明,丁康.包络分析方法及其在齿轮故障振动诊断中的应用[J].重庆大学学报(自然科学版),1995,18(1)：87-91.
[20]皮钧,王建军.包络谱细化的新方法及在齿轮故障诊断中的应用[J].拖拉机与农用运输车,2003,5(2)：10-12.
[21]白士红,孙斌.包络方法诊断齿轮箱故障[J].沈阳航空工业学院学报,2000,17(4)：73-74.
[22]丁康,王延春.传动箱齿轮和轴故障的振动诊断方法的研究[J].振动与冲击,1994,13(2)：26-32.
[23]Forrester B D. Gear Fault Detection Using the Wigner-Ville Distribution[A]. Transactions of the Institution of Engineers[C], Australia:Mechanical Engineering,1990, ME16(1):73-77.
[24]Baydar N, Ball A. Detection of Gear Deterioration Under Varying Load Conditions by Using the Instantaneous Power Spectrum[J]. Mechanical Systems and Signal Processing,2000, 14(6):907-921.
[25]周凤星,程耕国,高立新.小波分析在大型齿轮箱故障诊断中的应用[J].武汉科技大学学报(自然科学版),2003,26(3)：282-284.
[26]郑海波,李志远,陈心昭.基于连续小波变换的齿轮故障诊断方法研究[J].机械工程学报,2002,28(3)：69-73.
[27]Wang W J, McFadden P D. Application of Orthogonal Wavelets to Early Gear Damage Detection[J]. Mechanical System and Signal Processing,1995,9(5):497-507.
[28]王妙云.利用小波分析早期发现齿轮故障隐患[J].中国设备工程,2004,7(2)：37-39.
[29]徐科,杨德斌,徐金梧.小波变换在齿轮局部缺陷诊断中的应用[J].机械工程学报,1999,35(3)：105-107.
[30]张立明.人工神经网络的模型及其应用[M].上海：复旦大学出版社,1993.
[31]Yang P, Yam L. Theoretical and Experimental Study on Fault Diagnosis of Gear box [J]. Integrating Dynamics Condition Monitoring and Control for the 21st Century,1999, 9(2):117-121.
[32]李凌均.统计学习理论在机械设备智能诊断中的应用研究[D].西安：西安交通大学机械工程学院,2003.
[33]Vladimir N. Vapnik著,张学工译.统计学习理论的本质[M].北京：清华大学出版社,2004.
[34]肖健华,樊可清,吴今培,等.应用于故障诊断的SVM理论研究[J].振动、测试与诊断,2001,21(4)：258-262.
[35]张周锁,李凌均,何正嘉.基于支持向量机的多故障分类器及应用[J].机械科学与技术,2004,23(5)：536-538.
[36]马祥华,沈水福,布昭元.齿轮故障诊断专家系统[J].北京科技大学学报,1994,16(5)：435-439.
[37]申永军,杨绍普,刘献栋.齿轮故障诊断中的信号处理技术研究与展望[J].机械传动,2004,28(3)：1-5.
[38]朱小勇.齿轮箱故障诊断研究与试验台的设计[D].重庆：重庆大学机械工程学院,2001.
[39]吕志民,张武军,徐金梧,等.基于奇异谱的降噪方法及其在故障诊断技术中的应用[J].机械工程学报,1999.35(3)：85-88.
[40]宋友.转子系统碰摩故障诊断及振动信号的降噪处理[D].北京：北京航空航天大学电子工程系,2002.
[41]Yang Wen-Xian, Peter W Tse. Development of an advanced noise reduction method for vibration analysis based on singular value decomposition[J]. NDT&E International,2003, 36(2):419-432.
[42]温广瑞,张西宁,屈梁生.奇异值分解技术在声音信息分离中的应用[J].西安交通大学学报,2003,37(1)：37-40.
[43]袁小宏,史东峰.奇异值分解技术在齿轮箱故障诊断中的应用[J].振动、测试与诊断,2000,20(2)：91-96.
[44]李建,刘红星,屈梁生.探测信号中周期性冲击分量的奇异值分解技术[J].振动工程学报,2002,15(4)：415-418.
[45]Kanjilal P P, Palit S,Saha G. Fetal ECG extraction from single channel maternal ECG using singular value decomposition[J]. IEEE Trans.on Biomedical Engineering,1997,44(1): 51-59.
[46]刘献栋,杨绍普,申永军,等.基于奇异值分解的突变信息检测新方法及其应用[J].机械工程学报,2002,38(6)：102-105.
[47]何田,刘献栋,李其汉.噪声背景下检测突变信息的奇异值分解技术[J].振动工程学报,2006,19(1)：399-403.
[48]Giannakis G B, Swami A. New results on state-space and input-output identification of non-Gaussian processing using cumulants[A]. In:Proc. SPIE'87, San Diego, CA,1987, 826:199-205.
[49]Linsker R. An application of the principle of maximum information preservation to linear systems[J]. Advances in Neural Information Processing Systems,1989,35(2),1-3.
[50]Linsker R. Self-organization in a perceptual network[J]. Computer,1988,21(2):105-117.
[51]Heralt J, Jutten C. Blind separation of sources, Part I:An adaptive algorithm based on neuromimatic architecture[J]. Signal Processing,1991,24(1):1-10.
[52]Sorouchyari E. Blind separation of sources, Part Ⅲ:Stability Analysis[J], Signal Processing, 1991,24(1):21-29.
[53]Comon P. Blind separation of sources, Part Ⅱ:Problem statement[J]. Signal Processing, 1991,24(1):11-20.
[54]Tong L, Li R W, Soon V C. Indeterminacy and identifiability of blind identification [J]. IEEE Trans. On Circuits and Systems,1991,38(5):499-509.
[55]Burel G. Blind separation of sources:A nonlinear neural algorithm[J]. Neural Network, 1992,5(2):937-947.
[56]Comon P. Independent component analysis, a new concept[J]. Signal Processing,1994, 36(2):287-314.
[57]Cichocki A, Unbehauen R, Moszczynski L, et al. Anew on-line adaptive learning algorithm for blind separation of source signals[A]. In:ISANN94[C]. Taiwan,1994:406-411.
[58]Oja E, Karhunen J, Wang L, et al. Principle and independent components in neural networks-Recent developments[A]. In:Proc.7th Italian Workshop Neural Network, WIRN'95[C]. Vietri, Italy,1995:20-26.
[59]Karhunen J, Joutsensalo J. Repressentation and separation of signals using nonlinear PCA type learning[J]. Neural Network,1994,7(2):113-127.
[60]Bell A J, Sejnowski T J. An information-maximization approach to blind separation and blind deconvolution[J]. Neural Computation,1995,7(6):1004-1034.
[61]Delfosse N, Loubaton P. Adaptive blind separation of independent sources:A deflation approach[J]. Signal Processing,1995,45(2):59-83.
[62]Matsuoka K. A neural net for blind separation of non-stationary signals[J]. Neural Network, 1995,3(2):311-419.
[63]Cardoso J F, Laheld B H. Equivariant adaptive source separation[J]. IEEE Trans. Signal Processing,1996,44(10):3017-3030.
[64]Pearlmuter B A, Parra L C. A context-sensitive-generalization of ICA[A]. In: Proc. Int. Conf. Neural Information Processing, ICONIP'96[C]. HongKong:1996,151-157.
[65]Cardoso J F. Infomax and maximum likelihood for source separation[J]. IEEE Signal Processing Letters,1997,4(2):109-111.
[66]Girolami M, Fyfe C. Kurtosis extrema and identification of independent components:a neural network approach[A]. In:Proc. ICASSP'97[C].1997,4:3329-3333.
[67]Pham D T, Garat P. Blind separation of mixture of independent sources through a quasi-maximum likelihood approach[J]. IEEE Tans. Signal Processing,1997,45(7): 1712-1725.
[68]Amari S-I, Cichoki A. Adaptive blind signal processing-neural network approaches [J]. Proceedings of the IEEE,1998,86(10):2026-2046.
[69]Cardoso J F. Blind signal separation:statistical principles[J]. Proceedings of the IEEE,1998, 86(10):2009-2025.
[70]Valpola H. Nonlinear independent component analysis using ensemble learning:Theory [A]. In:Proc. ICA2000[C]. Helsinki, Finland:2000,251-256.
[71]Valpola H, Giannakopoulos X, Honkela A, et al. Nonlinear independent component analysis using ensemble learning:Experiments and discussion[A]. In:Proc. ICA2000[C]. Helsinki, Finland:2000,351-356.
[72]Cho K S, Lee S Y. Implementation of Infomax ICA Algorithm with Analog CMOS Circuits [A]. In:Proc. ICA2001[C]. San Diego, CA, USA:2001,70-73.
[73]Cardoso J F, Delabrouille J, G Patanchon. Independent component analysis of the cosmic microware background[A]. In:Proc. ICA2003[C]. Nara, Japan:2003,1111-1116.
[74]Yuan Z, Oja E. A FastICA Algorithm for Non-negative Independent Component Analysis [A]. In:Proc. ICA2004[C]. Granada, Spain:2004,1-8.
[75]Bell A J, et al. An information-maximization approach to blind separation and deconvolution [J]. Neural Computation,1995,7(2):1129-1159.
[76]Lee T W, et al. Independent component analysis using an extended infomax algorithm for sub-Gaussian and super-Gaussian sources[J]. Neural Computation,1999,11(2):409-433.
[77]Amari S-I. New learning in structural parameter space-natural Riemannian gradient [J]. Advance in Neural Information Processing Systems,1997,9(2):127-133.
[78]Amari S-I. Natural gradient works efficiently in learning[J]. Neural Computation,1998, 10(2):251-276.
[79]Hyvarinen A, et al. A fast fixed-point algorithm for independent component analysis [J]. Neural Computation,1997,9(7),1483-1492.
[80]Hyvarinen A. Fast and robust fixed-point algorithm for independent component analysis [J]. IEEE Trans. On Neural Network,1999,10(3),626-634.
[81]Cardoso J F. Higher order contrast for independent component analysis[J]. Neural Computation,1999,11(1):157-193.
[82]Cardoso J F. Blind beam forming for non-Gaussian signal[J]. IEEE. Proc. F,1993,140(6): 362-370.
[83]张贤达.现代信号处理[M].(第2版).北京：清华大学出版社,2002.
[84]杨福生,洪波.独立分量分析的原理与应用[M].北京：清华大学出版社,2006.
[85]马仓建,刘奕龙,陈海洋.盲信号处理[M].北京：国防工业出版社,2006.
[86]刘琚,何振亚.盲源分离和盲反卷积[J].电子学报,2002,30(4)：570-576.
[87]Alexander Ypma, Amir Leshem, Robert P W Duin. Blind separation of rotating machine sources:bilinear forms and convolutive mixtures[J]. Neuro computing-Special Issue on ICA/BSS,2002,35(2):123-134.
[88]Gelle G, Colas M. Delaunay G. Blind sources separation applied to rotating machines monitoring by acoustical and vibrations analysis[J], Mechanical Systems and Signal Processing,2000,14(3):427-442.
[89]Roan M J, Erling J G, Sibul L H. A new non-linear adaptive blind source separation approach to gear tooth failure detection and analysis[J]. Mechanical Systems and Signal Processing, 2002.16(5):719-740.
[90]Shen Yongjun, Yang Shaopu. A New Blind Source Separation Method and its Application to Fault Diagnosis of Rolling Bearing[J]. International Journal of Nonlinear Science and Numerical Simulation,2006,7(3):245-250.
[91]吴军彪,陈进,伍星.基于盲源分离技术的故障特征信号分离方法[J].机械强度,2002,24(4)：485-488.
[92]钟振茂,陈进,钟平.盲源分离技术用于机械故障诊断的研究初探[J].机械科学与技术,2002,21(2)：282-284.
[93]李舜酩.机械振动信号盲源分离的时域方法[J].应用力学学报,2005.22(4)：579-584.
[94]焦卫东,杨世锡,吴昭同.基于独立分量分析的噪声消除技术研究[J].浙江大学学报(工学版),2004,38(7)：872-876.
[95]李加文,李从心.基于鲁棒预白化的机械噪声信号盲分离[J].机械科学与技术,2005,24(12)：1499-1501.
[96]宋友,柳重堪,李其汉.基于三阶累计量的转子振动信号降噪方法研究[J].航空动力学报,2002,17(3)：363-366.
[97]任海峰,胡小平,吴建军.应用独立分量分析提取液体火箭发动机的故障特征[J].推进技术,2004,25(6)：481-483.
[98]陈仲生,杨拥民,沈国际.独立分量分析在直升机齿轮箱故障早期诊断中的应用[J].机械科学与技术,2004,23(4)：481-483.
[99]郝志华,马孝江,王奉涛.非平稳信号的盲源分离在机械故障诊断中的应用[J].振动与冲击,2006,25(1)：110-114.
[100]陈进,钟平.复杂声场中的频谱分离[J].振动与冲击,2002,21(1)：54-56.
[101]秦国军,莫芙蓉.滚动轴承含噪声谐波信号的欠确定盲源分离方法研究[J].国防科技大学学报,2006,28(1)：103-106.
[102]季忠,金涛,杨炯明,等.基于独立分量分析的消噪方法在旋转机械特征提取中的应用[J].中国机械工程,2005,16(1)：50-53.
[103]张永祥,明延涛,王洪磊.基于最小互信息准则的盲源分离在齿轮箱故障诊断中的应用[J].机械设计与制造,2006,6(2)：87-89.
[104]宋晓萍,廖明夫.盲源分离方法在旋转机械故障诊断中的应用[J].机械设计与制造,2006,3(2)：88-90.
[105]吴军彪,陈进,钟平,等.机械噪声故障特征提取的盲分离法及小波提纯法[J].上海交通大学学报,2003,37(5)：766-769.
[106]黄闯,侍洪波.基于独立分量分析(ICA)与小波变换的过程监测方法[J].吉林大学学报(工学版),2004,34(3)：465-470.
[107]焦卫东.基于互信息的小波特征提取方法及其在机械故障诊断中的应用[J].中国机械工程,2004,15(21)：1946-1949
[108]陈国金,梁军,钱积新.基于小波变换消噪和盲源信号分离的过程监控方法[J].化工学报,2005,56(5)：885-889.
[109]葛楠,刘月辉.独立分量分析在内燃机噪声信号分离技术中的应用[J].天津大学学报,2006,39(4)：454-457.
[110]李熠,何永勇,李志农,等.盲源分离和小波变换在碰摩声频信号分析中的应用研究[J].机械强度,2005,27(6)：719-724.
[111]吴小培,冯焕清,周何琴,等.基于独立分量分析的混合声信号分离[J].中国科学技术大学学报,2001,31(1)：68-73.
[112]宋友,柳重堪,李其汉.含噪振动信号中早期碰摩的故障检测研究[J].航空学报,2003,24(1)：32-35.
[113]杨世锡,焦卫东,吴昭同.独立分量分析基网络应用于旋转机械故障特征提取与分类[J].机械工程学报,2004,40(3)：45-49.
[114]杨世锡,焦卫东,吴昭同.基于独立分量分析特征提取的复合神经网络故障诊断法[J].振动工程学报,2004,17(4)：438-442.
[115]焦卫东,杨世锡,吴昭同.机械故障模式识别的ICA基神经网络方法[J].农业机械学报,2004,35(4)：151-154.
[116]焦卫东,杨世锡,吴昭同.复合ICA-SVM机械状态模式分类[J].中国机械工程,2004,15(1)：62-65.
[117]Widodo, Achmad, Yang, et al. Combination of independent component analysis and support vector machines for intelligent faults diagnosis of induction motors[J]. Expert Systems with Applications,2007,32(2):299-312
[118]焦卫东,杨世锡,钱苏翔,等.乘性噪声消除的同态变换盲源分离算法[J].浙江大学学报(工学版),2006,40(4)：581-584.
[119]焦卫东,杨世锡,吴昭同.机械声源信号的带通滤波盲分离[J].振动工程学报,2003,16(3)：344-348.
[120]何宁,谢磊,郭明等.基于独立成份的动态多变量过程的故障检测与诊断方法[J].化工学报,2005,56(4)：646-652.
[121]屈微.刘贺平,张德政.基于独立分量分析特征提取的故障诊断系统[J].北京科技大学学报,2006,28(7)：700-703.
[122]李良敏.基于遗传算法的盲源分离在轴承诊断中的应用[J].轴承,2005,9(2)：31-34.
[123]郝志华,马孝江.局域波法和独立成份分析在转子系统故障诊断上的应用[J].中国电机工程学报,2005,25(3)：84-88.
[124]胡红英,马孝江.局域波近似熵及其在机械故障诊断中的应用[J].振动与冲击,2006,25(4)：38-41.
[125]何清波,孔凡让,朱忠奎,等.盲卷积分离及其在机械振动信号消噪中的应用研究[J].振动与冲击,2006,25(2)：30-34.
[126]Cover T M, Thomas J A. Elements of information theory[M]. New York:John Wiley and Sons, LTD,1991.
[127]Hyvarinen A, Karhunen J, Oja E. Independent component analysis[M]. New York:John Wiley and Sons, LTD,2001,166.
[128]Cichocki A, Thawonmas R, Amari S. Sequential blind signal extraction in order specified by stochastic properties[J]. Electronics Letters,1997,33(1):64-65.
[129]Hyvarinen A, Oja E. Independent component analysis:algorithms and applications [J]. Neural Networks,2000,13(2):411-430.
[130]焦卫东.基于独立分量分析的旋转机械故障诊断方法研究[D].杭州：浙江大学机械与能源工程学院,2003.