基于单通道盲分离算法的大型风电机组早期机械故障诊断
|
摘要
由于大型风力发电机组工作的条件比较恶劣，而且运行时通常不是长时间稳定地处于一种载荷工况，而是随着风、电网、温度等条件的变化而不断的进行调整，因此机组的传动链所传递的载荷是不断变化的，这就会对传动链上的各个零部件提出一定的可靠性要求：一是零部件质量的可靠性，二是当零部件出现早期损伤时，能够及时的发现，以便作到故障的早发现早处理。对于第一点与设计和制造有关，本文不作讨论，这里只讨论第二种情况。
当风电机组出现故障时，故障零部件通常会产生具有一定特征的振动信号。但是在故障初期，这种故障特征并不明显。同时由于在风机运行时，许多零部件都会发出振动和噪音，振动传感器拾取信息时难免会受到强信号和噪声信号的影响,例如润滑和散热系统的运作、偏航和变桨机构的动作、电气系统的运行和发电机的励磁振动等，这些强信号和噪音之间还会互相干扰形成复杂的背景噪音，使早期故障特征振动信号湮没于背景噪音，提取真实准确的信息比较困难。同时，盲源分离算法对噪声很敏感，当利用该算法直接对混叠信号进行分离时，会造成很大的误差或得出错误的结论。因此，对采集到的振动信号进行盲分离前的强信号的去除以及降噪，对提高信噪比就显得尤为重要。
本文采用自相关方法和EEMD方法对采集的信号进行降噪；采用扩展多虚拟通道FastIca技术进行强信号分离；针对诊断领域中的单通道信号难以应用盲源分离方法的难点，采用EEMD-FastIca技术，可以满足盲源分离（BSS）算法的多入多出（MIMO）条件，实现信号的盲分离。这种方法的优点是既不必先知道源信号的数量，也不必先了解信号的产生和传递的参数，就能实现采集的信号中的各数据得盲分离；该方法可以提取风电机组传动链中的早期信号特征，提高了诊断的效率和准确性。为了验证方法的有效性，本文先通过仿真实验模拟出风电机组机械系统中的典型振动信号，并用上述方法分别进行分析测试，以确定其可以有效地分离信号。
机组的增速箱分离出特征振动信号；通过对佳木斯风电场采集的数据进行分析，诊断和分析一台1.5MW级风力发电机组的轴流风机散热器的早期故障信号，验证该方法在风电机组振动信号处理的有效性和基于EEMD-FastIca算法和强信号去除的虚拟通道盲分离方法及其扩展算法适用风电机组信号的处理、预测机械系统的早期故障。
As a result of the wind turbine working condition is usually abominable and astable.with the status changs of wind speed, power gird, temperature,the load case continuouslyadjusted too. so the load of the gear chain is continuosly changing. The reliability ofvarious parts should be guaranteed: The first, the parts quality, the second,if the parts growearly stage mechanical fault, it can be found. It is helpful for the equipment’s reliablyworking if we detect the fault in its early stage. For the first point,it related to the designand manufacture, the paper does not discuss, and We discuss the second point only.
When the wind turbine get out of order, the fault components usually make a typicalfeature signal in running. Because the incipient fault signal is weak and usually submergedin background noise and it is difficult to be extracted. The background noise contain thestrong signal and other noise of the wind turbine auxiliary mechanic system. If the signalhas some noise, the blind source separation algorithm would not work it out properly.Therefore, it is important to get rid of the strong signal and denoise from the mixture signal.signal is denoised by autocorrelation method and EEMD algorithm. the strong signal isEliminated by extend virtual channel FastIca technology from the mixture signal.It isnecessary to satisfy the demand of BSS's MIMO and extrac the incipient fault from thedata by EEMD-FastIca technology. The early stage knowledge needn't be grasped toprocessing the data by these methods.It can process the single channel signal by BSS In thecondition of the unknown number of the source signal.The organic combinationapplication of these methods can improve the efficiency and the accuracy of diagnosis. Inorder to verify the validity of these methods, by simulating the typical vibration signals of the turbines mechanical system, whather or not the the weak signal can be effectivelyseparated from the mixed signal.
By studying the frequency characteristic, An experiment is done by the wind turbinevibration diagnosis. by means of EEMD-FastIca algorithm, the characteristics signal issuccessful separated from the wind turbine test modal and the3MW wind turbine gearbox.the algorithm is effective in wind turbine signal processing;By means of virtual channelblind source separation techniques, the early fault signal is diagnosised and analysisedsuccessfully in a1.5MW wind turbine's axial flow fan. thus the EEMD-FastIca algorithmand the virtual channel blind separation method and the extended algorithm is applicable towind turbines in signal processing,and it apply to the prediction of mechanical early systemfault.
当风电机组出现故障时，故障零部件通常会产生具有一定特征的振动信号。但是在故障初期，这种故障特征并不明显。同时由于在风机运行时，许多零部件都会发出振动和噪音，振动传感器拾取信息时难免会受到强信号和噪声信号的影响,例如润滑和散热系统的运作、偏航和变桨机构的动作、电气系统的运行和发电机的励磁振动等，这些强信号和噪音之间还会互相干扰形成复杂的背景噪音，使早期故障特征振动信号湮没于背景噪音，提取真实准确的信息比较困难。同时，盲源分离算法对噪声很敏感，当利用该算法直接对混叠信号进行分离时，会造成很大的误差或得出错误的结论。因此，对采集到的振动信号进行盲分离前的强信号的去除以及降噪，对提高信噪比就显得尤为重要。
本文采用自相关方法和EEMD方法对采集的信号进行降噪；采用扩展多虚拟通道FastIca技术进行强信号分离；针对诊断领域中的单通道信号难以应用盲源分离方法的难点，采用EEMD-FastIca技术，可以满足盲源分离（BSS）算法的多入多出（MIMO）条件，实现信号的盲分离。这种方法的优点是既不必先知道源信号的数量，也不必先了解信号的产生和传递的参数，就能实现采集的信号中的各数据得盲分离；该方法可以提取风电机组传动链中的早期信号特征，提高了诊断的效率和准确性。为了验证方法的有效性，本文先通过仿真实验模拟出风电机组机械系统中的典型振动信号，并用上述方法分别进行分析测试，以确定其可以有效地分离信号。
机组的增速箱分离出特征振动信号；通过对佳木斯风电场采集的数据进行分析，诊断和分析一台1.5MW级风力发电机组的轴流风机散热器的早期故障信号，验证该方法在风电机组振动信号处理的有效性和基于EEMD-FastIca算法和强信号去除的虚拟通道盲分离方法及其扩展算法适用风电机组信号的处理、预测机械系统的早期故障。
As a result of the wind turbine working condition is usually abominable and astable.with the status changs of wind speed, power gird, temperature,the load case continuouslyadjusted too. so the load of the gear chain is continuosly changing. The reliability ofvarious parts should be guaranteed: The first, the parts quality, the second,if the parts growearly stage mechanical fault, it can be found. It is helpful for the equipment’s reliablyworking if we detect the fault in its early stage. For the first point,it related to the designand manufacture, the paper does not discuss, and We discuss the second point only.
When the wind turbine get out of order, the fault components usually make a typicalfeature signal in running. Because the incipient fault signal is weak and usually submergedin background noise and it is difficult to be extracted. The background noise contain thestrong signal and other noise of the wind turbine auxiliary mechanic system. If the signalhas some noise, the blind source separation algorithm would not work it out properly.Therefore, it is important to get rid of the strong signal and denoise from the mixture signal.signal is denoised by autocorrelation method and EEMD algorithm. the strong signal isEliminated by extend virtual channel FastIca technology from the mixture signal.It isnecessary to satisfy the demand of BSS's MIMO and extrac the incipient fault from thedata by EEMD-FastIca technology. The early stage knowledge needn't be grasped toprocessing the data by these methods.It can process the single channel signal by BSS In thecondition of the unknown number of the source signal.The organic combinationapplication of these methods can improve the efficiency and the accuracy of diagnosis. Inorder to verify the validity of these methods, by simulating the typical vibration signals of the turbines mechanical system, whather or not the the weak signal can be effectivelyseparated from the mixed signal.
By studying the frequency characteristic, An experiment is done by the wind turbinevibration diagnosis. by means of EEMD-FastIca algorithm, the characteristics signal issuccessful separated from the wind turbine test modal and the3MW wind turbine gearbox.the algorithm is effective in wind turbine signal processing;By means of virtual channelblind source separation techniques, the early fault signal is diagnosised and analysisedsuccessfully in a1.5MW wind turbine's axial flow fan. thus the EEMD-FastIca algorithmand the virtual channel blind separation method and the extended algorithm is applicable towind turbines in signal processing,and it apply to the prediction of mechanical early systemfault.
引文
[1] T.I.Salsbury,R.C.Diamond.Fault detection in HVAC systems using model-based feedforwardcontrol. Energy and Buildings,2001(33):403~415.
[2]单光坤.兆瓦级风电机组状态监测及故障诊断研究：(博士学位论文）.沈阳:沈阳工业大学,2008.
[3] IEC61400-1(GB18451.l).风电机组设计要求,第八章:控制和保护系统.
[4]屈梁生.机械故障诊断学.上海:科技出版社,1986.
[5]周勃,基于盲分离的空调机组故障振声诊断研究：(博士学位论文）.沈阳:沈阳工业大学,2008.
[6]盛兆顺,尹畸岭.设备状态监测与故障诊断技术及应用.北京:化学工业出版社,2003.
[7]关惠玲,韩捷.设备故障诊断专家系统原理及实践.北京:机械工业出版社,2000.
[8] House JohnM, Vaezi Nejad, J Michael. An expert rule set for fault detection in air handlingunits.ASHRAETrans,2001,107(1):858~871.
[9] S.W. Wang, J.B. Wang. Law-based sensor fault diagnosis and validation for buildingair-conditioning systems. HVAC&R Research,1999,5(4):353~380.
[10]陈长征,周永.小波神经网络法在柴油机故障诊断中的应用,内燃机学报,2002,20(1):89~91.
[11] G. Betta, C. Liguori, and A. Pietrosanto. A multi-application FFT-analyzer based on a DSParchitecture. IEEE Trans.Instrum. Meas.,2001:825~832.
[12] Giovanni Betta, Consolatina Liguori, Alfredo Paolillo. A DSP-based FFT-Analyzer for the faultdiagnosis of rotating machine based on vibration analysis. IEEE Transactions on Instrumentationand Measurement,2002,51(6):316~1322.
[13] D. Ngo. Fuzzy indentication approach in air-conditioning system. International Journal of HVACand R Research,2006,7(1):183~192.
[14] Wilson Q. Wanga, M. Farid Golnaraghi, Fathy Ismail. Prognosis of machine health condition usingneuro-fuzzy systems.Mechanical Systems and Signal Processing,2004(18):813~831.
[15] Jesús Manuel, Fernández Salido, Shuta Murakami. A comparison of two learning mechanisms forthe automatic design of fuzzy diagnosis systems for rotating machinery. Applied Softcomputing,2004(4):413~422.
[16]虞和济,陈长征,张省等.基于神经网络的智能诊断.北京:冶金工业出版社,2000.
[17] B. Samanta, K. R. Balushi. Condition classification of small reciprocating compressor forrefrigerators using artificial neural networks and support vector machines. Mechanical Systemand Signal Processing,2005,19(2):371~390.
[18] A. K. Nandi. Neural-network-based motor rolling bearing fault diagnosis. IEEE Trans. Ind.Electron,1997,47:1060~1069.
[19] Y.C. Chang, F.A. Lin, C.H. Lin. Optimal chiller sequencing by branch and bound method forsaving energy. Energy Conversion and Management,2005,46(12–14):2158~2172.
[20] J. Burnett. Online adaptive control for optimizing variable-speed pumps of indirect water-cooledchilling systems. Applied Thermal Engineering,2001,21(11):1083~1103.
[21] Kyusung Kim, Alexander G.Parlos. Induction motor fault diagnosis based on neuropredictors andwavelet signal processing. IEEE/ASME Trans on Mechatronics,2002,7(2):201~219.
[22] Meyer Y. Wavelets algorithms and applications. J. SIAM,1993.
[23] B.A Paya, I. Esat. Artificial neural network based fault diagnostics of rotating machinery usingwavelet transform as a preprocessor. Mechanical Systems and Signal Processing,2004:640~654.
[24] T. Matsuura. An application of neural network for selecting feature parameters in machinerydiagnosis. Journal of Materials Processing Technology,2004:1~5.
[25] T. Kaewkongka, Y.H. Joe Au, R. Rakowski, B.E. Jones. Continuous wavelet transform and neuralnetwork for condition monitoring of dynamic machinery. IEEE Instrumentation and MeasurementTechnology Conference Budapest,2001:21~23.
[26] Achmad Widodo, Bo-Suk Yang. Support vector machine in machine condition monitoring andfault diagnosis. Mechanical Systems and Signal Processing,2007(21):2560~2574.
[27] R. Fang. Induction machine rotor diagnosis using support vector machines and rough set. LectureNotes in Artificial Intelligence,2006(4114):631~636.
[28] A. Widodo, B.S. Yang, T. Han. Combination of independent component analysis and supportvector machine for intelligent faults diagnosis of induction motors. Expert System withApplication,2007(32):299~312.
[29] S.F. Yuan, F.L. Chu. Support vector machines-based fault diagnosis for turbo-pump rotor.Mechanical System and Signal Processing,2006,20(4):939~952.
[30] S.F. Yuan, F.L. Chu. Fault diagnosis based on support vector machine with parameter optimizationby artificial immunization algorithm. Mechanical System and Signal Processing,2007,21(3):1318~1330.
[31] B. Samanta. Gear fault detection using artificial neural networks and support vector machines withgenetic algorithms. Mechanical Systems and Signal Processing,2004,18(3):625~644.
[32] C.W. Hsu, C.J. Lin. A comparison of methods for multi-class support vector machines. IEEETransactions on Neural Networks,2002(13):415~425.
[33] K.Kim, A.G.Parlos. Model-based fault diagnosis of induction motors using non-stationary signalsegmentation. Mechanical Systems and Signal processing,2002,16(2):223~253.
[34] I.Daubechies. The wavelet transform, time-frequency localization and signal analysis. IEEE Trans.Information Theory,1999,36(5):961~1005.
[35] Wan Lianghon., Liu Yibing., Feng Dongliang. Application of wavelet packets analysis to faultdiagnose of rolling bearings. Modern Electric Power,2004,21(1):24~26.
[36] Isermann R. Supervision, fault detection and fault-diagnosis methods. Control Engineering andPractice,1997,5(5):639~652.
[37] R.N. Mahanty, P.B. Dutta Gupta. Application of RBF neural network to fault classification andlocation in transmission lines. IEEE Proc-Gener. Transm. Distrib.,2004,151:201~212.
[38] M. Zacksenhouse, S. Braun, M. Feldman. Toward helicopter gearbox diagnostics from a smallexamples. Mechanical Systems and Signal Processing,2000,14(4):523~543.
[39] L.B. Jack, A.K. Nandi. Fault detection using support vector machines and artificial neural network,augmented by genetic algorithms. Mechanical System and Signal Processing,2002,16:373~390.
[40] B. Samanta, K.R. Al-Balushi, S.A. Al-Araimi. Artificial neural network and support vectormachine with genetic algorithm for bearing fault detection. Engineering Application of ArtificialIntelligence,2003,16:657~665.
[41] Wang, S. and Cui, J. Sensor-fault detection, diagnosis and estimation for centrifugal chiller systemsusing principal-component analysis method. Applied Energy,2005,8(23):197~213.
[42]李舜酩.振动信号的盲源分离技术及应用.北京:航空工业出版社,2011.
[43] A. J. Bell, T. J. Seinowski. An information maximization approach to blind separation and blinddeconvolution. Neural Computation,1995(7):1129~1159.
[44] M.J. Roan, J.G.. Erling, L.H. Sibul. A new non-linear adaptive blind source separation approach togear tooth failure detection and analysis. Mechanical Systems and Signal Processing,2007,16:719~740.
[45] Guillaume Gelle, Maxime Cloas, Christine Serviere. Blind source separation: a new pre-processingtool for rotating machines monitoring. IEEE. Transactions on Instrumentation and Measurement,2003,52:790~795.
[46] C. Serviere., P. Fabry. Blind source separation of noisy harmonic signals for rotating machinediagnosis. Journal of Sound and Vibration,2004,272:317~339.
[47] Gwo-Ching Liao, Ta-Peng Tsao: Application of fuzzy neural networks and artificial intelligencefor load forecasting. Electric Power Systems Research,2004,70:237~244.
[48] Xinhua Xu, Fu Xiao, Shengwei Wang. Enhanced chiller sensor fault detection, diagnosis andestimation using wavelet analysis and principal component analysis methods. Applied ThermalEngineering,2007:1~12.
[49]马建仓,牛奕龙,陈海洋,盲信号处理.北京：国防工业出版社,2006.
[50] J.K. Tugnait. Identification and deconvolution of multichannel linear non-Gaussian processes usinghigher order statistics and inverse filter criteria. IEEE Transactions on Signal Processing,1997,45(3):658~672.
[51] Massoud Babaie-Zadeha, Christian Jutten A general approach for mutual information minimizationand its application to blind source separation. Signal Processing,2005,85:975~995.
[52] P. Haves, T.I. Salsbury, J.A. Wright. Condition monitoring in HVAC subsystem using firstprinciples models. ASHRAE Transactions,1996,102(1):519~527.
[53] J.E. Jackson. A User’s Guide to Principal Components. John Wiley&Sons,1991.
[54] X.Q. Jin, Z.M. Du. Fault tolerant control of outdoor air and AHU supply air temperature in VAVair conditioning systems using PCA method. Applied Thermal Engineering,2006,26(11–12):1226~1237.
[55] R. Peled, S. Braun, M. Zacksenhouse. A blind deconvolution separation of multiple sources, withapplication to bearing diagnostics. Mechanical Systems and Signal Processing,2005,19:1181~1195.
[56] G. Gelle, M. Colas, G. Delaunay, Blind sources separation applied to rotating machines monitoringby acoustical and vibrations analysis. Mechanical Systems and Signal Processing,2000,14(3):427~442.
[57]何慧龙,机电设备微弱特征提取与诊断方法研究：(博士学位论文）.天津：天津大学,2006.
[58]李舜酩.转子振动故障信号的盲分离.航空动力学报,2005,20(5):751~756.
[59] J. Antoni, F. Guillet, M. El Badaoui. Blind separation of convolved cyclostationary processes[J].Signal Processing,2005,85:1~66.
[60] Roal M.J., Erling J.G. A new non-linear adaptive blind separation approach to gear tooth failuredetection and analysis. Mechanical Systems and Signal Processing,2002,16:719~740.
[61] Roger Boustany. A subspace method for the blind extraction of a cyclostationary source: Appli-cation to rolling element bearing diagnostics. Mechanical Systems and Signal Proce-ssing,2005,19:1245~1259.
[62] J. Antoni, F. Bonnardot, A. Raad, M. El Badaoui. Cyclostationary modelling of rotating machinevibration signals[J]. Mechanical Systems and Signal Processing,2004,18(6):1285~1314.
[63] J. Antoni, F. Guillet, M. El Badaoui. Blind separation of convolved cyclostationary processes[J].Signal Processing,2005,85:1~66.
[64] A. Ferre′ol, P. Chevalier. On the behavior of current second and higher order blind sourceseparation methods for cyclostationary sources[J]. IEEE Transactions on Signal Processing,2000,48(6):1712~1725.
[65] T.J. Sejnowski. A non-linear information maximization approach that performs blind decon-volution approach. Neural Computation,1998(12):571~583.
[66]张新成,杜志勇,周俊青.盲源分离技术及其应用[J].电声技术,2004,4:4~6.
[67]何继爱,王维芳,李力舟.盲源信号分离方法研究[J].无线通信技术,2009,4:10~14.
[68] S.ARMARI, J.F.CARDOSO. Blind source separation-semiparametric statistical approach [J].IEEETrans. Signal Processing,1997,45(11):2692~2700.
[69]宋妍,田玉刚,贾小霞.基于极大似然估计采样一致性准则的遥感影像配准参数解算方法研究[J].测绘科学,2011,36(1):51~54.
[70] D.T.PHAM, J. CARDOSO. Blind separation of instantaneous mixtures of nonstationary sources[J].IEEE Trans. Signal Processing,2001,49(9):1837~1848.
[71]易叶青.基于进化算法的盲源信号分离:（硕士学位论文）.长沙:湖南大学,2005.
[72]吴新杰,崔春阳.基于粒子群算法的盲源信号分离[J].辽宁大学学报(自然科学版),2009,6(2):125~128.
[73]杨福生,洪波.独立分量分析的原理与应用[M].清华大学出版社,2006.
[74]胡婧,张更新,熊纲要.盲信号分离技术综述[J].数字通信世界,2010,4:64~68.
[75]田丽娜.噪声环境下语音信号盲分离的研究:(硕士学位论文）.武汉:武汉科技大学,2008.
[76] Hyvarinen A, Oja E, A fast fixed-point algorithm for independent component analysis, NeuralComputation,1997,9(7):1483~1492.
[77] Hyvarinen A,Karhunen J,Oja E. Independent component analysis [M].New York:J.Wiley,2001.
[78]周成,刘钊.基于独立分量分析的单通道语音降噪算法研究[J].激光与红外,2005,35(5):374~377.
[79] Alexander YPMA, Learning methods for machine vibration analysis and healthmonitoring[DoctorDissertation], Delft: Delft University of Technology,2001.
[80] G. Gelle, M. Colas, G. Delaunay, Blind sources separation applied to rotatingmachines monitoringby acoustical and vibrations analysis, MechanicalSystems and Signal Processing,2000,14(3):427~442.
[81]吴小培,詹长安,周荷琴等,采用独立分量分析方法消除信号中的工频干扰,中国科学技术大学学报,2000,30(6)：671~676,638.
[82]吴小培,李晓辉,孔敏等,基于独立分量分析的谐波估计与消除,电工技术学报,2003,18(4)：56~60.
[83]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,中国机械工程,2005,16(1)：50~53.
[84]顾江,张光新,刘国华等,基于独立分量分析的声发射信号去噪方法,江南大学学报(自然科学版),2008,7(1)：55~59.
[85] C. Jutten, J. Herault, Blind separation of sources, Part1:An adaptive algorithmbased on neuro-mimetic structure, Signal Processing,1991,24:1~10.
[86] A.J.Bell,T. Sejnowski,An information maximization approach to blind separa-tion and blind deco-volution, Neural Computation,1995,7(6):1129~1159.
[87] Norden E.Huang, Zheng Shen, Stenen R.Long. The empirical mode decomposition and the Hilbertspectrum for nonlinear and non-stationary time series analysis[C]. Proc.R.Soc,London,1998,454:903~995.
[88] J.F. Cardoso, High-order constrasts for independent component analysis, Neural Computation,1999,11(1):157~192.
[89] Amari S., Cichocki A., Yang H.H., A new learning algorithm for blind signalseparation, Advancesin Neural Information Processing Systems, Cambridge:MIT Press,1996,8:757~763.
[90] HyvarinenA, Oja E,Afast fixed-point algorithm for independent component analysis, NeuralComputation,1997,9(7):1483~1492.
[91] P.Comon,Independent Component Analysis,A New Concept, Signal Processing,1994,36:287~314.
[92]肖瑞,基于独立分量分析的盲源分离方法的研究:（硕士学位论文）.西安：西安理工大学,2003.
[93]徐春生,微弱信号检测及机械故障诊断系统研究:（硕士学位论文）.天津：天津大学,2008.
[94]赵艳菊,强噪声背景条件下机械设备微弱信号的提取与检测技术研究:（硕士学位论文）.天津：天津大学,2008.
[95] Norden E.Huang,Zheng Shen,Stenen R.Long. A new view of nonlinear water waves:The HilbertSpectrum[J].Annual Review of Fluid Mechanics,1999,31:417~457.
[96]赵雯雯,曾兴雯.一种新的EMD去噪方法[J].电子科技,2008,21(5):30~36.
[97]付荣荣,基于经验模态分解和单通道盲源信号分离测量两相流速度:（硕士学位论文）.辽宁：辽宁大学,2011.
[98]张韧,旋转机械故障特征提取技术及其系统研究:（硕士学位论文）.杭州：浙江大学,2004
[99]刘佳，单通道盲源分离及其在水声信号处理中的应用研究：(博士学位论文).哈尔滨：哈尔滨工程大学,2011.
[100] WU Z H,HUANG N E. Ensemble empirical mode decomposition: a noise assisted data analys ismethod [J].Advances in Adaptive Data Analysis, Theory and Applications,2009,1(1):141.
[101] Benbouzid M., Nejjar H., Beguenane R., Vieira M., Induction MotorAsymmetrical FaultsDetection Using Advanced Signal Processing Techniques, IEEE Trans.Energy Conversion,1999,14(2):147~52.
[102]刘振兴,尉宇,赵敏,陈正澎,基于RELAX频谱分析法的鼠龙式异步电动机转子故障诊断,中国电机工程学报,2006,26(22)：146~150.
[103]谢明,丁康.频谱分析的校正方法,振动工程学报,1994,7(2):172~179.
[104]陈长征,胡立新,周勃等.设备振动分析与故障诊断技术.北京：科学出版社,2006.
[105]李士心.小波域中值滤波器设计的研究.电子科技大学学报,2003,32(l):19~21.
[106]潘泉,孟晋丽,张磊,等.小波滤波方法及应用.电子与信息学报,29(1):236~242.
[107]文莉,刘正士.小波去噪的舫中方法.剖旺业大学学报,2003,25(2):168~170.
[108]谢明,丁康.频谱分析的校正方法,振动工程学报,1994,7(2):172~179.
[109]孟涛,廖明夫,李辉.齿轮故障诊断的时延相关解调法.航空动力学报,2003,18(1):109~113.
[110]陈隽,李想.运用总体经验模态分解的疲劳信号降噪方法.振动.测试与诊断,2011,30(1)：16~18.
[111]张玉，基于振动信号分析的齿轮箱故障诊断.仪器仪表与分析检测，2011.1:20~24.
[2]单光坤.兆瓦级风电机组状态监测及故障诊断研究：(博士学位论文）.沈阳:沈阳工业大学,2008.
[3] IEC61400-1(GB18451.l).风电机组设计要求,第八章:控制和保护系统.
[4]屈梁生.机械故障诊断学.上海:科技出版社,1986.
[5]周勃,基于盲分离的空调机组故障振声诊断研究：(博士学位论文）.沈阳:沈阳工业大学,2008.
[6]盛兆顺,尹畸岭.设备状态监测与故障诊断技术及应用.北京:化学工业出版社,2003.
[7]关惠玲,韩捷.设备故障诊断专家系统原理及实践.北京:机械工业出版社,2000.
[8] House JohnM, Vaezi Nejad, J Michael. An expert rule set for fault detection in air handlingunits.ASHRAETrans,2001,107(1):858~871.
[9] S.W. Wang, J.B. Wang. Law-based sensor fault diagnosis and validation for buildingair-conditioning systems. HVAC&R Research,1999,5(4):353~380.
[10]陈长征,周永.小波神经网络法在柴油机故障诊断中的应用,内燃机学报,2002,20(1):89~91.
[11] G. Betta, C. Liguori, and A. Pietrosanto. A multi-application FFT-analyzer based on a DSParchitecture. IEEE Trans.Instrum. Meas.,2001:825~832.
[12] Giovanni Betta, Consolatina Liguori, Alfredo Paolillo. A DSP-based FFT-Analyzer for the faultdiagnosis of rotating machine based on vibration analysis. IEEE Transactions on Instrumentationand Measurement,2002,51(6):316~1322.
[13] D. Ngo. Fuzzy indentication approach in air-conditioning system. International Journal of HVACand R Research,2006,7(1):183~192.
[14] Wilson Q. Wanga, M. Farid Golnaraghi, Fathy Ismail. Prognosis of machine health condition usingneuro-fuzzy systems.Mechanical Systems and Signal Processing,2004(18):813~831.
[15] Jesús Manuel, Fernández Salido, Shuta Murakami. A comparison of two learning mechanisms forthe automatic design of fuzzy diagnosis systems for rotating machinery. Applied Softcomputing,2004(4):413~422.
[16]虞和济,陈长征,张省等.基于神经网络的智能诊断.北京:冶金工业出版社,2000.
[17] B. Samanta, K. R. Balushi. Condition classification of small reciprocating compressor forrefrigerators using artificial neural networks and support vector machines. Mechanical Systemand Signal Processing,2005,19(2):371~390.
[18] A. K. Nandi. Neural-network-based motor rolling bearing fault diagnosis. IEEE Trans. Ind.Electron,1997,47:1060~1069.
[19] Y.C. Chang, F.A. Lin, C.H. Lin. Optimal chiller sequencing by branch and bound method forsaving energy. Energy Conversion and Management,2005,46(12–14):2158~2172.
[20] J. Burnett. Online adaptive control for optimizing variable-speed pumps of indirect water-cooledchilling systems. Applied Thermal Engineering,2001,21(11):1083~1103.
[21] Kyusung Kim, Alexander G.Parlos. Induction motor fault diagnosis based on neuropredictors andwavelet signal processing. IEEE/ASME Trans on Mechatronics,2002,7(2):201~219.
[22] Meyer Y. Wavelets algorithms and applications. J. SIAM,1993.
[23] B.A Paya, I. Esat. Artificial neural network based fault diagnostics of rotating machinery usingwavelet transform as a preprocessor. Mechanical Systems and Signal Processing,2004:640~654.
[24] T. Matsuura. An application of neural network for selecting feature parameters in machinerydiagnosis. Journal of Materials Processing Technology,2004:1~5.
[25] T. Kaewkongka, Y.H. Joe Au, R. Rakowski, B.E. Jones. Continuous wavelet transform and neuralnetwork for condition monitoring of dynamic machinery. IEEE Instrumentation and MeasurementTechnology Conference Budapest,2001:21~23.
[26] Achmad Widodo, Bo-Suk Yang. Support vector machine in machine condition monitoring andfault diagnosis. Mechanical Systems and Signal Processing,2007(21):2560~2574.
[27] R. Fang. Induction machine rotor diagnosis using support vector machines and rough set. LectureNotes in Artificial Intelligence,2006(4114):631~636.
[28] A. Widodo, B.S. Yang, T. Han. Combination of independent component analysis and supportvector machine for intelligent faults diagnosis of induction motors. Expert System withApplication,2007(32):299~312.
[29] S.F. Yuan, F.L. Chu. Support vector machines-based fault diagnosis for turbo-pump rotor.Mechanical System and Signal Processing,2006,20(4):939~952.
[30] S.F. Yuan, F.L. Chu. Fault diagnosis based on support vector machine with parameter optimizationby artificial immunization algorithm. Mechanical System and Signal Processing,2007,21(3):1318~1330.
[31] B. Samanta. Gear fault detection using artificial neural networks and support vector machines withgenetic algorithms. Mechanical Systems and Signal Processing,2004,18(3):625~644.
[32] C.W. Hsu, C.J. Lin. A comparison of methods for multi-class support vector machines. IEEETransactions on Neural Networks,2002(13):415~425.
[33] K.Kim, A.G.Parlos. Model-based fault diagnosis of induction motors using non-stationary signalsegmentation. Mechanical Systems and Signal processing,2002,16(2):223~253.
[34] I.Daubechies. The wavelet transform, time-frequency localization and signal analysis. IEEE Trans.Information Theory,1999,36(5):961~1005.
[35] Wan Lianghon., Liu Yibing., Feng Dongliang. Application of wavelet packets analysis to faultdiagnose of rolling bearings. Modern Electric Power,2004,21(1):24~26.
[36] Isermann R. Supervision, fault detection and fault-diagnosis methods. Control Engineering andPractice,1997,5(5):639~652.
[37] R.N. Mahanty, P.B. Dutta Gupta. Application of RBF neural network to fault classification andlocation in transmission lines. IEEE Proc-Gener. Transm. Distrib.,2004,151:201~212.
[38] M. Zacksenhouse, S. Braun, M. Feldman. Toward helicopter gearbox diagnostics from a smallexamples. Mechanical Systems and Signal Processing,2000,14(4):523~543.
[39] L.B. Jack, A.K. Nandi. Fault detection using support vector machines and artificial neural network,augmented by genetic algorithms. Mechanical System and Signal Processing,2002,16:373~390.
[40] B. Samanta, K.R. Al-Balushi, S.A. Al-Araimi. Artificial neural network and support vectormachine with genetic algorithm for bearing fault detection. Engineering Application of ArtificialIntelligence,2003,16:657~665.
[41] Wang, S. and Cui, J. Sensor-fault detection, diagnosis and estimation for centrifugal chiller systemsusing principal-component analysis method. Applied Energy,2005,8(23):197~213.
[42]李舜酩.振动信号的盲源分离技术及应用.北京:航空工业出版社,2011.
[43] A. J. Bell, T. J. Seinowski. An information maximization approach to blind separation and blinddeconvolution. Neural Computation,1995(7):1129~1159.
[44] M.J. Roan, J.G.. Erling, L.H. Sibul. A new non-linear adaptive blind source separation approach togear tooth failure detection and analysis. Mechanical Systems and Signal Processing,2007,16:719~740.
[45] Guillaume Gelle, Maxime Cloas, Christine Serviere. Blind source separation: a new pre-processingtool for rotating machines monitoring. IEEE. Transactions on Instrumentation and Measurement,2003,52:790~795.
[46] C. Serviere., P. Fabry. Blind source separation of noisy harmonic signals for rotating machinediagnosis. Journal of Sound and Vibration,2004,272:317~339.
[47] Gwo-Ching Liao, Ta-Peng Tsao: Application of fuzzy neural networks and artificial intelligencefor load forecasting. Electric Power Systems Research,2004,70:237~244.
[48] Xinhua Xu, Fu Xiao, Shengwei Wang. Enhanced chiller sensor fault detection, diagnosis andestimation using wavelet analysis and principal component analysis methods. Applied ThermalEngineering,2007:1~12.
[49]马建仓,牛奕龙,陈海洋,盲信号处理.北京：国防工业出版社,2006.
[50] J.K. Tugnait. Identification and deconvolution of multichannel linear non-Gaussian processes usinghigher order statistics and inverse filter criteria. IEEE Transactions on Signal Processing,1997,45(3):658~672.
[51] Massoud Babaie-Zadeha, Christian Jutten A general approach for mutual information minimizationand its application to blind source separation. Signal Processing,2005,85:975~995.
[52] P. Haves, T.I. Salsbury, J.A. Wright. Condition monitoring in HVAC subsystem using firstprinciples models. ASHRAE Transactions,1996,102(1):519~527.
[53] J.E. Jackson. A User’s Guide to Principal Components. John Wiley&Sons,1991.
[54] X.Q. Jin, Z.M. Du. Fault tolerant control of outdoor air and AHU supply air temperature in VAVair conditioning systems using PCA method. Applied Thermal Engineering,2006,26(11–12):1226~1237.
[55] R. Peled, S. Braun, M. Zacksenhouse. A blind deconvolution separation of multiple sources, withapplication to bearing diagnostics. Mechanical Systems and Signal Processing,2005,19:1181~1195.
[56] G. Gelle, M. Colas, G. Delaunay, Blind sources separation applied to rotating machines monitoringby acoustical and vibrations analysis. Mechanical Systems and Signal Processing,2000,14(3):427~442.
[57]何慧龙,机电设备微弱特征提取与诊断方法研究：(博士学位论文）.天津：天津大学,2006.
[58]李舜酩.转子振动故障信号的盲分离.航空动力学报,2005,20(5):751~756.
[59] J. Antoni, F. Guillet, M. El Badaoui. Blind separation of convolved cyclostationary processes[J].Signal Processing,2005,85:1~66.
[60] Roal M.J., Erling J.G. A new non-linear adaptive blind separation approach to gear tooth failuredetection and analysis. Mechanical Systems and Signal Processing,2002,16:719~740.
[61] Roger Boustany. A subspace method for the blind extraction of a cyclostationary source: Appli-cation to rolling element bearing diagnostics. Mechanical Systems and Signal Proce-ssing,2005,19:1245~1259.
[62] J. Antoni, F. Bonnardot, A. Raad, M. El Badaoui. Cyclostationary modelling of rotating machinevibration signals[J]. Mechanical Systems and Signal Processing,2004,18(6):1285~1314.
[63] J. Antoni, F. Guillet, M. El Badaoui. Blind separation of convolved cyclostationary processes[J].Signal Processing,2005,85:1~66.
[64] A. Ferre′ol, P. Chevalier. On the behavior of current second and higher order blind sourceseparation methods for cyclostationary sources[J]. IEEE Transactions on Signal Processing,2000,48(6):1712~1725.
[65] T.J. Sejnowski. A non-linear information maximization approach that performs blind decon-volution approach. Neural Computation,1998(12):571~583.
[66]张新成,杜志勇,周俊青.盲源分离技术及其应用[J].电声技术,2004,4:4~6.
[67]何继爱,王维芳,李力舟.盲源信号分离方法研究[J].无线通信技术,2009,4:10~14.
[68] S.ARMARI, J.F.CARDOSO. Blind source separation-semiparametric statistical approach [J].IEEETrans. Signal Processing,1997,45(11):2692~2700.
[69]宋妍,田玉刚,贾小霞.基于极大似然估计采样一致性准则的遥感影像配准参数解算方法研究[J].测绘科学,2011,36(1):51~54.
[70] D.T.PHAM, J. CARDOSO. Blind separation of instantaneous mixtures of nonstationary sources[J].IEEE Trans. Signal Processing,2001,49(9):1837~1848.
[71]易叶青.基于进化算法的盲源信号分离:（硕士学位论文）.长沙:湖南大学,2005.
[72]吴新杰,崔春阳.基于粒子群算法的盲源信号分离[J].辽宁大学学报(自然科学版),2009,6(2):125~128.
[73]杨福生,洪波.独立分量分析的原理与应用[M].清华大学出版社,2006.
[74]胡婧,张更新,熊纲要.盲信号分离技术综述[J].数字通信世界,2010,4:64~68.
[75]田丽娜.噪声环境下语音信号盲分离的研究:(硕士学位论文）.武汉:武汉科技大学,2008.
[76] Hyvarinen A, Oja E, A fast fixed-point algorithm for independent component analysis, NeuralComputation,1997,9(7):1483~1492.
[77] Hyvarinen A,Karhunen J,Oja E. Independent component analysis [M].New York:J.Wiley,2001.
[78]周成,刘钊.基于独立分量分析的单通道语音降噪算法研究[J].激光与红外,2005,35(5):374~377.
[79] Alexander YPMA, Learning methods for machine vibration analysis and healthmonitoring[DoctorDissertation], Delft: Delft University of Technology,2001.
[80] G. Gelle, M. Colas, G. Delaunay, Blind sources separation applied to rotatingmachines monitoringby acoustical and vibrations analysis, MechanicalSystems and Signal Processing,2000,14(3):427~442.
[81]吴小培,詹长安,周荷琴等,采用独立分量分析方法消除信号中的工频干扰,中国科学技术大学学报,2000,30(6)：671~676,638.
[82]吴小培,李晓辉,孔敏等,基于独立分量分析的谐波估计与消除,电工技术学报,2003,18(4)：56~60.
[83]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,中国机械工程,2005,16(1)：50~53.
[84]顾江,张光新,刘国华等,基于独立分量分析的声发射信号去噪方法,江南大学学报(自然科学版),2008,7(1)：55~59.
[85] C. Jutten, J. Herault, Blind separation of sources, Part1:An adaptive algorithmbased on neuro-mimetic structure, Signal Processing,1991,24:1~10.
[86] A.J.Bell,T. Sejnowski,An information maximization approach to blind separa-tion and blind deco-volution, Neural Computation,1995,7(6):1129~1159.
[87] Norden E.Huang, Zheng Shen, Stenen R.Long. The empirical mode decomposition and the Hilbertspectrum for nonlinear and non-stationary time series analysis[C]. Proc.R.Soc,London,1998,454:903~995.
[88] J.F. Cardoso, High-order constrasts for independent component analysis, Neural Computation,1999,11(1):157~192.
[89] Amari S., Cichocki A., Yang H.H., A new learning algorithm for blind signalseparation, Advancesin Neural Information Processing Systems, Cambridge:MIT Press,1996,8:757~763.
[90] HyvarinenA, Oja E,Afast fixed-point algorithm for independent component analysis, NeuralComputation,1997,9(7):1483~1492.
[91] P.Comon,Independent Component Analysis,A New Concept, Signal Processing,1994,36:287~314.
[92]肖瑞,基于独立分量分析的盲源分离方法的研究:（硕士学位论文）.西安：西安理工大学,2003.
[93]徐春生,微弱信号检测及机械故障诊断系统研究:（硕士学位论文）.天津：天津大学,2008.
[94]赵艳菊,强噪声背景条件下机械设备微弱信号的提取与检测技术研究:（硕士学位论文）.天津：天津大学,2008.
[95] Norden E.Huang,Zheng Shen,Stenen R.Long. A new view of nonlinear water waves:The HilbertSpectrum[J].Annual Review of Fluid Mechanics,1999,31:417~457.
[96]赵雯雯,曾兴雯.一种新的EMD去噪方法[J].电子科技,2008,21(5):30~36.
[97]付荣荣,基于经验模态分解和单通道盲源信号分离测量两相流速度:（硕士学位论文）.辽宁：辽宁大学,2011.
[98]张韧,旋转机械故障特征提取技术及其系统研究:（硕士学位论文）.杭州：浙江大学,2004
[99]刘佳，单通道盲源分离及其在水声信号处理中的应用研究：(博士学位论文).哈尔滨：哈尔滨工程大学,2011.
[100] WU Z H,HUANG N E. Ensemble empirical mode decomposition: a noise assisted data analys ismethod [J].Advances in Adaptive Data Analysis, Theory and Applications,2009,1(1):141.
[101] Benbouzid M., Nejjar H., Beguenane R., Vieira M., Induction MotorAsymmetrical FaultsDetection Using Advanced Signal Processing Techniques, IEEE Trans.Energy Conversion,1999,14(2):147~52.
[102]刘振兴,尉宇,赵敏,陈正澎,基于RELAX频谱分析法的鼠龙式异步电动机转子故障诊断,中国电机工程学报,2006,26(22)：146~150.
[103]谢明,丁康.频谱分析的校正方法,振动工程学报,1994,7(2):172~179.
[104]陈长征,胡立新,周勃等.设备振动分析与故障诊断技术.北京：科学出版社,2006.
[105]李士心.小波域中值滤波器设计的研究.电子科技大学学报,2003,32(l):19~21.
[106]潘泉,孟晋丽,张磊,等.小波滤波方法及应用.电子与信息学报,29(1):236~242.
[107]文莉,刘正士.小波去噪的舫中方法.剖旺业大学学报,2003,25(2):168~170.
[108]谢明,丁康.频谱分析的校正方法,振动工程学报,1994,7(2):172~179.
[109]孟涛,廖明夫,李辉.齿轮故障诊断的时延相关解调法.航空动力学报,2003,18(1):109~113.
[110]陈隽,李想.运用总体经验模态分解的疲劳信号降噪方法.振动.测试与诊断,2011,30(1)：16~18.
[111]张玉，基于振动信号分析的齿轮箱故障诊断.仪器仪表与分析检测，2011.1:20~24.
© 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 |