复杂机械基于数据的建模与故障诊断
|
摘要
机械设备健康状态监测的运行振动信号通常是故障诊断的重要数据来源,使用这些数据进行故障诊断可以通过建立基于信号的线性或非线性模型实现,也可以直接从振动信号中提取故障特征。使用何种诊断策略最为有效,则要根据数据性质的判断加以确定。如果数据来自于明显的线性系统,则采用基于线性模型的诊断方法是恰当的;若数据是非线性的,使用基于非线性模型的诊断方法可以取得好的效果;若数据显示机械设备进入混沌振动状态,则要提取混沌特征进行故障诊断。因此,本文研究了某些非线性数据特征的检验方法,例如使用双谱分析检验数据的非线性特征,并用于检验齿轮箱振动数据的特性;使用Lyapunov指数定量描述混沌程度,并以振动筛为例,研究筛帮不同部位的混沌性强弱。此外,通过相关分析研究各部分振动数据的相关性,以制定诊断策略。
提出几何-物理空间概念,把大的系统的所有数据按物理空间划分成小区域的数据集,实现物理分区。在聚类分析的规则下,对时间上不断扩展的数据集进行基于距离的分类,实现数据分区。使用主元分析将高维数据空间降维成低维数据空间,在保持原有有用信息量几乎不变的情况下,去除冗余信息,仅使用较低的维数和较少的数据量来表示原有数据,并给出仿真算例。
本文讨论了线性系统模型与可用于非线性系统的神经网络模型。从神经网络模型的拓扑结构优化、输出数据的个数、延迟步数、隐层神经元的个数和激活函数等方面优化神经网络的辨识能力,即提高辨识精度与加快辨识速度。从而提高了用于故障诊断的神经网络模型辨识的实时性。
提出模型确定性的概念:将辨识系统的谱特征作为目标特征,对权值矩阵行数据做盒状图分析。权值离群值愈少,谱特征确定性愈好,也就是说模型是确定的,可以代表一定时间内的系统区域。
本文提出了基于虚拟响应谱序列的诊断方法。在辨识出的精确模型基础上,使用并行仿真,获得系统对不同幅值的虚拟正弦或脉冲激励的响应,分析得到的正弦系列响应谱图和脉冲系列响应谱图,即可得到系统的动态特征,也可用于诊断线性或非线性系统的故障,从而提高了故障诊断的可信度。将这种方法应用于工程结构的诊断,取得较好的结果。
Operation vibration signals of mechanical equipment health monitoring are usually the important source of data for fault diagnosis. In order to diagnose faults via these data, linear or nonlinear model based on signal can be used. It can be used to extract fault features directly from the vibration signals too. The effective diagnostic strategy is determined in accordance with results of inspection for nature of the data. If the data comes from the obvious linear system, the diagnosis methods based on linear model are appropriate. If the data are non-linear, the diagnosis method based on nonlinear model can achieve good results. If the data show that mechanical equipment is into the chaotic vibration state, the chaotic features are extracted for fault diagnosis. Therefore, this paper studies some test method of nonlinear data, such as bispectrum analysis that is used to test the characteristics of gear vibration data. Lyapunov index is used to describe chaos quantificationally.
Propose the concept of geometry - physical space. All data of the large system are divided into smaller regional data sets, and get the physical partition.
Under the rules in the cluster analysis, the data set that expands with time is classed under distance-based classification.
The high dimensional data space is reduced into low-dimensional data space using PCA , the original information content is almost unchanged , redundant data is dislodged , the small amount of low dimension data are used to represent the original data, and simulation examples are given.
Linear system models and neural network models that applie to nonlinear systems are discussed. The recognition capability of neural network is optimized by considering topological structure optimization, item count of output data, delay step, item count of hidden layer neuron, activation function, etc. It is that identification accuracy and speed are improved. Thus Real time property of identifying neural network models is improved.
The concept of model determinacy is provided. Spectrum characteristics of the identified system that is target feature, boxplots of weight matrix row data are analyzed. Spectrum signature presents best determinacy, when there are less outliers of weight values.
In this paper a Fault diagnosis method based on virtual response spectrum sequences is proposed. The parallel simulation is performed based on identified accurate models to obtain response sequences correspond to different amplitudes of virtual sine or impulse excition. The series of sine response spectrum and pulse response spectrum can be used to analyze dynamic characteristics of system. The series of response spectra can be used for fault diagnosis of linear or nonlinear systems too, thereby increasing the reliability of fault diagnosis. This method has been applied successfully to the diagnosis of engineering structures.
提出几何-物理空间概念,把大的系统的所有数据按物理空间划分成小区域的数据集,实现物理分区。在聚类分析的规则下,对时间上不断扩展的数据集进行基于距离的分类,实现数据分区。使用主元分析将高维数据空间降维成低维数据空间,在保持原有有用信息量几乎不变的情况下,去除冗余信息,仅使用较低的维数和较少的数据量来表示原有数据,并给出仿真算例。
本文讨论了线性系统模型与可用于非线性系统的神经网络模型。从神经网络模型的拓扑结构优化、输出数据的个数、延迟步数、隐层神经元的个数和激活函数等方面优化神经网络的辨识能力,即提高辨识精度与加快辨识速度。从而提高了用于故障诊断的神经网络模型辨识的实时性。
提出模型确定性的概念:将辨识系统的谱特征作为目标特征,对权值矩阵行数据做盒状图分析。权值离群值愈少,谱特征确定性愈好,也就是说模型是确定的,可以代表一定时间内的系统区域。
本文提出了基于虚拟响应谱序列的诊断方法。在辨识出的精确模型基础上,使用并行仿真,获得系统对不同幅值的虚拟正弦或脉冲激励的响应,分析得到的正弦系列响应谱图和脉冲系列响应谱图,即可得到系统的动态特征,也可用于诊断线性或非线性系统的故障,从而提高了故障诊断的可信度。将这种方法应用于工程结构的诊断,取得较好的结果。
Operation vibration signals of mechanical equipment health monitoring are usually the important source of data for fault diagnosis. In order to diagnose faults via these data, linear or nonlinear model based on signal can be used. It can be used to extract fault features directly from the vibration signals too. The effective diagnostic strategy is determined in accordance with results of inspection for nature of the data. If the data comes from the obvious linear system, the diagnosis methods based on linear model are appropriate. If the data are non-linear, the diagnosis method based on nonlinear model can achieve good results. If the data show that mechanical equipment is into the chaotic vibration state, the chaotic features are extracted for fault diagnosis. Therefore, this paper studies some test method of nonlinear data, such as bispectrum analysis that is used to test the characteristics of gear vibration data. Lyapunov index is used to describe chaos quantificationally.
Propose the concept of geometry - physical space. All data of the large system are divided into smaller regional data sets, and get the physical partition.
Under the rules in the cluster analysis, the data set that expands with time is classed under distance-based classification.
The high dimensional data space is reduced into low-dimensional data space using PCA , the original information content is almost unchanged , redundant data is dislodged , the small amount of low dimension data are used to represent the original data, and simulation examples are given.
Linear system models and neural network models that applie to nonlinear systems are discussed. The recognition capability of neural network is optimized by considering topological structure optimization, item count of output data, delay step, item count of hidden layer neuron, activation function, etc. It is that identification accuracy and speed are improved. Thus Real time property of identifying neural network models is improved.
The concept of model determinacy is provided. Spectrum characteristics of the identified system that is target feature, boxplots of weight matrix row data are analyzed. Spectrum signature presents best determinacy, when there are less outliers of weight values.
In this paper a Fault diagnosis method based on virtual response spectrum sequences is proposed. The parallel simulation is performed based on identified accurate models to obtain response sequences correspond to different amplitudes of virtual sine or impulse excition. The series of sine response spectrum and pulse response spectrum can be used to analyze dynamic characteristics of system. The series of response spectra can be used for fault diagnosis of linear or nonlinear systems too, thereby increasing the reliability of fault diagnosis. This method has been applied successfully to the diagnosis of engineering structures.
引文
[1] H. Endo, R.B. Randall and C. Gosselin, Differential diagnosis of spall vs. cracks in the gear tooth fillet region: Experimental validation [J],Mechanical Systems and Signal Processing, 2009, 23(3): 563-986.
[2]王楠,陈长征,孙长城,周勃,基于应力波与小波分析的低速滚动轴承故障诊断研究[J],振动工程学报,2007,20(3):280-284
[3]程发斌,汤宝平,刘文艺一种抑制维格纳分布交叉项的方法及在故障诊断中应用[J],中国机械工程2008,19(14):1727-1731
[4]孙云岭,朴甲哲,张永祥Wigner-Ville时频分布在内燃机故障诊断中的应用[J],中国机械工程,2004, 15(6):505-507
[5] W.X. Yang , X.M. Ren, Detecting impulses in mechanical signals by wavelets [J], Journal on Applied Signal Processing , 2004, (8): 1156–1162
[6] W.X. Yang , P.W. Tse, An advanced strategy for detecting impulses in mechanical signals[J], Journal of Vibration and Acoustics , 2005,127 (3): 280–284
[7] M.A. Jafarizadeh, R. Hassannejad, M.M. Ettefagh and S. Chitsaz, Asynchronous input gear damage diagnosis using time averaging and wavelet filtering [J], Mechanical Systems and Signal Processing, 2008,22(1):172-201
[8] Zhinong Li, Yongyong He, Fulei Chu, Application of the blind source separation in machine fault diagnosis: A review and prospect [J],Mechanical Systems and Signal Processing, In Press, Corrected Proof, Available online 27 April 2005
[9]叶红仙,杨世锡,杨将新,多振源卷积混合的时域盲源分离算法[J],机械工程学报,2009,45 (1):189-194
[10] Xun Wang,Uwe Kruger,George W. Irwin,Nonlinear PCA With the Local Approach for Diesel Engine Fault Detection and Diagnosis[J],IEEE Transactions on Control Systems Technology, 2008, 16(1): 122-129
[11]孙健,章卫国,宁东方,基于神经网络的飞控系统故障诊断[J],测控技术,2008,27(5):65-67
[12] Xiaofeng Liu, Lin Ma and Joseph Mathew,Machinery fault diagnosis based on fuzzy measure and fuzzy integral data fusion techniques[J],Mechanical Systems and Signal Processing, 2009,23(3): 690-700
[13] Samuel da Silva, Milton Dias Júnior, Vicente Lopes Junior, Michael J. Brennan,Structural damage detection by fuzzy clustering [J],Mechanical Systems and Signal Processing, 2008, 22(7): 1636-1649
[14] Wilson Wang, Fathy Ismail, Farid Golnaraghi,A Neuro-Fuzzy Approach to Gear System Monitoring [J],IEEE Transactions on Fuzzy Systems, 2004, 12( 5): 710-723
[15] Wilson Wang, Derek Kanneg, An integrated classifier for gear system monitoring [J],Mechanical Systems and Signal Processing, 2009, 23(4): 1298-1312
[16] B. Ling , M. M. Khonsari, Online Tribology Ball Bearing Fault Detection and Identification [C], Proc. of SPIE 2007, Vol. 6555:65551A
[17] Leite Daniel F., Hell Michel B., Diez Patricia H., Gariglio Bernardo S. L., Nascimento Lucas O., Costa Pyramo, Real-Time Model-Based Fault Detection and Diagnosis for Alternators and Induction Motors [C], Electric Machines and Drive Conference, 2007 IEEE International: 202-207
[18] Feng Zhao, Xenofon Koutsoukos, Horst Haussecker, Patrick Cheung, Monitoring and Fault Diagnosis of Hybrid Systems [J],IEEE Transactions on Systems, Man, and Cybernetics—Part B: Cybernetics, 2005, 35( 6): 1225-1240
[19] S L Chen, R J K Wood, L Wang, R Callan , H E G Powrie, Wear detection of rolling element bearings using multiple-sensing technologies and mixture-model-based clustering method[C],Proc. IMechE 2008, Vol.222 Part O:J. Risk and Reliability: 207-218
[20] Paolo Pennacchi, NicolòBachschmid, Andrea Vania, Gian Antonio Zanetta and Luca Gregori , Use of modal representation for the supporting structure in model based fault identification of large rotating machinery: part 1—theoretical remarks[J], Mechanical Systems and Signal Processing, 2006, 20(3): 662-681
[21] Christof Devriendt, Gert De Sitter, Steve Vanlanduit, Patrick Guillaume, Operational modal analysis in the presence of harmonic excitations by the use of transmissibility measurements[J],Mechanical Systems and Signal Processing, 2009, 23( 3): 621-635
[22] E. Pierro, E. Mucchi, L. Soria, A. Vecchio, On the vibro-acoustical operational modal analysis of a helicopter cabin[J],Mechanical Systems and Signal Processing, 2009,23(4): 1205-1217
[23] Christof Devriendt, Gert De Sitter, Steve Vanlanduit, Patrick Guillaume, Operational modal analysis in the presence of harmonic excitations by the use of transmissibility measurements[J],Mechanical Systems and Signal Processing, 2009,23(3):.621-635
[24] R. Pintelon, B. Peeters, P. Guillaume, Continuous-time operational modal analysis in the presence of harmonic disturbances[J],Mechanical Systems and Signal Processing, 2008, 22(5): 1017-1035
[25] R. Pintelon and J. Schoukens, System Identification: A Frequency Domain Approach[M], IEEE Press, Piscataway (2001)
[26] B. Peeters, G. Lowet, H. Van Der Auweraer and J. Leuridan, A new procedure for modal parameter estimation[J], Sound and Vibration ,2004,38 (1) : 24–29
[27] B. Peeters, H. Van Der Auweraer, P. Guillaume and J. Leuridan, The polymax frequency-domain method: a new standard for modal parameter estimation[J], Shock and Vibration ,2004,11 (3–4) : 395–409
[28]熊诗波,王然风,梁义维,轧机自激振动诊断和结构动力学修改[J],机械工程学报,2005, 41(7): 147-151
[29] D. Hanson, R.B. Randall, J. Antoni, D.J. Thompson, T.P. Waters and R.A.J. Ford , Cyclostationarity and the cepstrum for operational modal analysis of mimo systems—Part I: Modal parameter identification[J] , Mechanical Systems and Signal Processing, 2007, 21(6): 2441-2458.
[30] Ljung L, Convergence Analysis of Paramet ric Identification Methods. IEEE Trans. on Automatic Control ,1978 ,AC- 23 :770 - 783.
[31]徐小平,王峰,胡钢,系统辨识研究的现状[J],现代电子技术,2007, 30(15):112-116
[32]段丽玮,吴志华,徐志伟,基于ARX模型的飞机尾翼压电结构系统辨识研究[J],压电与声光, 2008,30(6):760-762
[33]李秀英,韩志刚,非线性系统辨识方法的新进展[J],自动化技术与应用,2004,23(10):5-7
[34]朱豫才,过程控制的多变量系统辨识[M],国防科技大学出版社,湖南,2005
[35]朱燕飞,谭洪舟,章云,一类非线性系统盲辨识算法及仿真研究[J],系统仿真学报,2008,20(14):3782-3784
[36]侯媛彬,系统辨识及其MATLAB仿真[M],科学出版社,北京,2004
[37]於东军,郑宇杰,吴小俊,杨静宇,基于Kernel-SOM的非线性系统辨识及模型运行收敛性分析[J],电子与信息学报,2008,30(8):1928-1931
[38]徐祖华,赵均,钱积新,基于操作轨迹LPV模型的非线性辨识[J],系统工程理论与实践,2008,28(7):155-159
[39]胡钋,具有维纳-哈默斯坦模型结构非线性系统的一种辨识方法[J],电子学报,2009,(9):1907-1911
[40]庞世伟,于开平,邹经湘,利用NARMA模型辨识非线性时变结构系统[J],哈尔滨工业大学学报, 2008,40(1):12-16
[41]张恒,李积德,赵晓东,基于系统辨识方法求解船舶非线性运动响应[J],大连海事大学学报,2008,34(4):67-71
[42]王宏伟,马广富,王子才,模糊辨识理论与应用研究发展[J],系统仿真学报,2000,12(2): 87-126
[43]王士同,於东军,非线性系统的模糊辨识误差分析,软件学报[J],2000,11(4):447-452
[44]王然风,基于支持向量回归技术的大型复杂机电设备故障诊断研究与应用[D],博士学位论文,2005
[45] Takagi T , Sugeno M. Fuzzy Identification of Systems and Its Application to Modeling and Cont rol. IEEE Trans.on Systems ,Man and Cybernetics [J],1985 ,15 (1) :116 - 132.
[46] Johansen T A ,Murray - Smith R. On the Interpretation and Identification of Dynamic Takagi - Sugeno Fuzzy Models [J ] . IEEE Trans. on Fuzzy Systems , 2000 , 8 (3) : 297- 313.
[47] Leec H , Tengc C. Identification and Cont rol of DynamicSystems Using Recurrent Fuzzy Network [ J ] . IEEE Trans. on Fuzzy Systems ,2000 ,8 (4) :349 - 366.
[48]李人厚,张平安,关于模糊辨识的理论与应用实际问题,控制理论与应用[J], 1995,12 (2):129 - 137
[49]邵青,冯汝鹏,非线性系统模糊辨识的新方法[J],控制与决策,2001 ,16(1) :83 - 85
[50]刘福才,关新平,裴润,基于一种新模糊模型的非线性系统模糊辨识[J],控制理论与应用, 2003 ,20(1) :113 - 116
[51]李娟,模糊辨识方法研究进展[J],莱阳农学院学报,(17)1:71-76
[52] Y. F. Wang, D. H. Wang, T. Y. Chai. Modeling and control compensation of nonlinear friction using adaptive fuzzy systems [J]. Mechanical Systems and Signal Processing, 2009, 23: 2445-2457
[53]李超顺,周建中,安学利,向秀桥,李清清,基于T_S模糊模型的水轮机调节系统辨识[J].武汉大学学报(工学版),2010,43(1):108-111
[54]赵志刚,吕恬生,王庚,基于Takagi-Sugen模糊模型的小型无人直升机系统辨识[J],上海交通大学学报,2008,42(5):856-859
[55]王广军,王志杰,陈红,基于递阶分解聚类的非线性系统递推模糊辨识[J],控制与决策,2009, 24(12):1846-1850
[56]于龙,肖建,白裔峰,基于批量模糊学习矢量量化的模糊系统辨识[J],控制与决策,2007,22(8),903-906
[57]易继锴,侯媛彬.智能控制技术[M].北京:北京工业大学出版社,1999
[58]李茶玲,孙德保,遗传算法在系统辨识中的应用[J ] ,华中理工大学学报,1998 ,26 (7) :57 - 58
[59]王晓鹏,万敏,一种基于遗传算法的动力学系统辨识方法[J],飞行力学,2003,21(2):56-58
[60]姜波,江秉文,基于遗传算法的非线性系统模型参数估计[J],控制理论与应用, 2000, 17 (1) :150 - 152
[61]边润强,陈增强,袁著祉,一种改进的遗传算法及其在系统辨识中的应用[J],控制与决策, 2000 ,15(5) :623 - 625
[62]徐洪泽,一种具有变异性杂交的遗传算法及其在系统辨识中的应用[J],哈尔滨工业大学学报,1997 ,29(4) :74 - 75
[63]蒙祖强,蔡自兴,一种基于并行遗传算法非线性系统辨识方法[J],控制与决策. 2003 ,18 (3) :367– 374
[64]吴茂林,黄声华,永磁同步电机非线性参数辨识[J].电工技术学报,2009,24(8):65-68
[65]商秀芹,卢建刚,孙优贤,改进遗传规划算法在系统辨识中的应用[J],东南大学学报(自然科学版),2009,39(Sup(I)):22-26
[66]龚固丰,章兢,何敏,王炼红,混合编码免疫算法在非线性系统辨识中的应用[J],系统仿真学报,2009,21(12):3561-3564
[67]徐小平,钱富才,刘丁,王峰,基于PSO算法的系统辨识方法[J].系统仿真学报,2008,20(13):3525-3528
[68]赵宝江,李士勇,基于蚁群聚类算法的非线性系统辨识[J],控制与决策,2007,(10):1193-1200
[69]翟永杰,尚雪莲,韩璞等,SVR在传感器故障诊断中的仿真研究[J],系统仿真学报,2004, 16( 6):1257-1279
[70]马勇,黄德先,金以慧,基于支持向量机的软测量建模方法[J],信息与控制,2004,33(4): 417-421
[71] J A K. Suykens,Nonlinear modeling and support vector machines[C],Proc of the 18th IEEE Conf on Instrumentation and Measurement Technology .Budapest,2001:287-294
[72]黄宴委,吴惕华,赵静一,回归型支持向量机的系统辨识及仿真[J],计算机仿真,2004,21(5): 41-44
[73] J A K Suykens,Least squares support vector machines for classification and nonlinear modelling,Neural Network World,2000,10 (1～2) :29～48
[74]蔡艳宁,胡昌华,辨识非线性MIMO系统的多输出ε-SVR模型研究[J].控制与决策,2008,23(7):813-816
[75]魏东,张明廉,基于神经网络的非线性模型辨识[J],北京建筑工程学院学报,2004,20(4):26-30
[76]苑希民,崔广涛,张玉峰,流激振动系统的神经网络辨识和预报[J],水利学报,1999,(3):13-20
[77]李保奎,神经网络辨识方法及其在轧钢控制中的应用[J],北京理工大学学报, 2002,22(3): 311-314
[78]刘国栋,用神经网络辨识非线性大滞后系统的研究[J],信息与控制,2000, 29(3):225-229
[79]饶文碧,程洪斌,方复兴,结构损伤神经网络辨识系统的实现[J],武汉理工大学学报, 2002, 24(1):28-30
[80] Vicky Rouss, Willy Charon, Giansalvo Cirrincione. Neural model of the dynamic behavior of a non-linear mechanical system[J]. Mechanical Systems and Signal Processing, 2009, 23:1145-1159
[81] Leandro dos Santos Coelho, Marcelo Wicthoff Pesso? a. Nonlinear identification using a B-spline neural network and chaotic immune approaches[J]. Mechanical Systems and Signal Processing, 2009, 23: 2418-2434
[82]吴德会.非线性动态系统的Wiener神经网络辨识法[J].控制理论与应用,2009,26(11):1192-1196
[83]于开平,董好志.基于前向神经网络的时变非线性结构系统辨识快速递推最小二乘法[J].振动工程学报,2007,20(5):468-472
[84]陈华伟,钟化兰,靳蕃.基于双向权值调整算法的神经网络非线性系统辨识[J].铁道学报,2007,10(5):48-53
[85]陈涵,邓长虹,李大路.基于循环神经网络的动态等值模型辨识[J].高电压技术,2008,34(5):1001-1004
[86]奚海蛟,张晓林.基于Elman网络的共轴式直升机动力学系统辨识[J].北京航空航天大学学报,2008,34(7):861-864
[87]岑豫皖,叶金杰,潘紫微.非线性状态空间方法辨识电液伺服控制系统[J].机械工程学报,2008,44(12):80-85
[88]刘益剑,方彦军,马宝萍.滑动数据窗口驱动的贝叶斯-高斯网络及其在非线性系统辨识中的应用[J].控制理论与应用,2009,26(12):1435-1438
[89]胡玉玲,曹建国.基于模糊神经网络的动态非线性系统辨识研究[J].系统仿真学报,2007,19(3):560-562
[90]刘胜,赵红.遗传算法—模糊聚类动态模糊神经网络辨识[J].哈尔滨工程大学学报,2008,29(8):825-830
[91]葛宏伟,李小琳,梁艳春,何湘东.基于免疫粒子群优化的一种动态递归神经网络辨识与控制非线性系统[J].吉林大学学报(工学版),2008,38(4):858-864
[92]刘本德,胡昌华.基于Volterra频域核辨识的非线性模拟电路故障诊断[J].控制与决策,2009,24(8):1167-1171
[93]张贤达,现代信号处理[M],北京大学出版社,2002
[94]陈仲生,基于MATLAB7.0的统计信息处理[M],湖南科学技术出版社,2005
[95] John G.Proakis等著,汤俊等译,统计信号处理算法[M],清华大学出版社.2006.3:500～506
[96]苏文斌,温熙森,史维祥,故障诊断中非线性耦合特征提取的研究[J],西安交通大学学报, 1999,33(1)
[97]韩敏,混沌时间序列预测理论与方法[M],中国水利水电出版社,2007,5
[98]王鼐,非线性动力学方法在时间序列分析中的应用[D],复旦大学博士论文,2005
[99]刘秉正,彭建华,非线性动力学[M],高等教育出版社,2004.
[100]朱明武,李永新,卜雄洙,测试信号处理与分析[M],北京航空航天大学出版社2006
[101]佟德纯,姚宝恒,工程信号处理与设备诊断[M],科学出版社,2008
[102]张善文,雷英杰,冯有前,MATLAB在时间序列分析中的应用[M],西安电子科技大学出版社,2007
[103] Andrew R.Webb著,王萍,杨培龙,罗颖昕译,统计模式识别[M],电子工业出版社2004
[104]温熙森,模式识别与状态监控[M],科学出版社,2007
[105]张志武,孙新娟,刘雪梅.利用自组织特征映射神经网络实现数据分区[J].数据库与信息处理,2007,10:130-132
[106]齐志.基于SOM神经网络的聚类可视化方法研究[D].东北师范大学硕士学位论文,2009
[107]王莉,王正欧.TGSOM:一种用于数据聚类的动态自组织映射神经网络[J].电子与信息学报,2003,25(3):313-319
[108]闻新,周露等.MATLAB神经网络仿真与应用[M].北京:科学出版社,2006
[109]周建新,罗晓玲,付传秀.自组织特征映射神经网络的区域经济发展聚类分析[J].贵州大学学报(自然科学版),2008,25(2):127-130
[110]倪步喜,章丽芙,姚敏.基于SOFM网络的聚类分析[J].计算机工程与设计,2006,27(5):855-857
[111]李戈,邵峰晶,朱本浩.基于神经网络聚类的研究[J].青岛大学学报,2001,16(4):1-4
[112] Johnson R A, Wichern D W.实用多元统计分析(第四版)[M].陆璇,葛余博,赵衡秀等译,清华大学出版社,2001
[113]朱永生,实验数据多元统计分析[M],科学出版社,2009
[114]张杰.多变量统计过程控制[M].北京:化学工业出版社,2000.
[115]齐晓慧等,现代控制理论及应用[M],国防工业出版社,2007
[116]魏东,非线性系统神经网络参数预测及控制,机械工业出版社, 2008:29-31
[117] Norgaard,M. (2000). Neural network based system identification toolbox.Technical Report. 00-E-891, Department of Automation, Technical University of Denmark.
[118]张代远,神经网络新理论与方法[M],清华大学出版社,2006
[119]熊晓燕,高分辨率扭振测量方法及其应用[J],振动、测试与诊断,2003,23(1)
[120]唐向宏,李齐良,时频分析与小波变换[M],科学出版社,2008
[121]陈恩伟,机器人动态特性及动力学参数辨识研究[M],合肥工业大学出版社,2008
[122]曹建福,韩崇昭,方洋旺,非线性系统理论及应用[M],西安交通大学出版社,2006
[123] J.C. Peyton Jones,Simplified computation of the Volterra frequency response functions of non-linear systems,Mechanical Systems and Signal Processing 21 (2007): 1452–1468
[2]王楠,陈长征,孙长城,周勃,基于应力波与小波分析的低速滚动轴承故障诊断研究[J],振动工程学报,2007,20(3):280-284
[3]程发斌,汤宝平,刘文艺一种抑制维格纳分布交叉项的方法及在故障诊断中应用[J],中国机械工程2008,19(14):1727-1731
[4]孙云岭,朴甲哲,张永祥Wigner-Ville时频分布在内燃机故障诊断中的应用[J],中国机械工程,2004, 15(6):505-507
[5] W.X. Yang , X.M. Ren, Detecting impulses in mechanical signals by wavelets [J], Journal on Applied Signal Processing , 2004, (8): 1156–1162
[6] W.X. Yang , P.W. Tse, An advanced strategy for detecting impulses in mechanical signals[J], Journal of Vibration and Acoustics , 2005,127 (3): 280–284
[7] M.A. Jafarizadeh, R. Hassannejad, M.M. Ettefagh and S. Chitsaz, Asynchronous input gear damage diagnosis using time averaging and wavelet filtering [J], Mechanical Systems and Signal Processing, 2008,22(1):172-201
[8] Zhinong Li, Yongyong He, Fulei Chu, Application of the blind source separation in machine fault diagnosis: A review and prospect [J],Mechanical Systems and Signal Processing, In Press, Corrected Proof, Available online 27 April 2005
[9]叶红仙,杨世锡,杨将新,多振源卷积混合的时域盲源分离算法[J],机械工程学报,2009,45 (1):189-194
[10] Xun Wang,Uwe Kruger,George W. Irwin,Nonlinear PCA With the Local Approach for Diesel Engine Fault Detection and Diagnosis[J],IEEE Transactions on Control Systems Technology, 2008, 16(1): 122-129
[11]孙健,章卫国,宁东方,基于神经网络的飞控系统故障诊断[J],测控技术,2008,27(5):65-67
[12] Xiaofeng Liu, Lin Ma and Joseph Mathew,Machinery fault diagnosis based on fuzzy measure and fuzzy integral data fusion techniques[J],Mechanical Systems and Signal Processing, 2009,23(3): 690-700
[13] Samuel da Silva, Milton Dias Júnior, Vicente Lopes Junior, Michael J. Brennan,Structural damage detection by fuzzy clustering [J],Mechanical Systems and Signal Processing, 2008, 22(7): 1636-1649
[14] Wilson Wang, Fathy Ismail, Farid Golnaraghi,A Neuro-Fuzzy Approach to Gear System Monitoring [J],IEEE Transactions on Fuzzy Systems, 2004, 12( 5): 710-723
[15] Wilson Wang, Derek Kanneg, An integrated classifier for gear system monitoring [J],Mechanical Systems and Signal Processing, 2009, 23(4): 1298-1312
[16] B. Ling , M. M. Khonsari, Online Tribology Ball Bearing Fault Detection and Identification [C], Proc. of SPIE 2007, Vol. 6555:65551A
[17] Leite Daniel F., Hell Michel B., Diez Patricia H., Gariglio Bernardo S. L., Nascimento Lucas O., Costa Pyramo, Real-Time Model-Based Fault Detection and Diagnosis for Alternators and Induction Motors [C], Electric Machines and Drive Conference, 2007 IEEE International: 202-207
[18] Feng Zhao, Xenofon Koutsoukos, Horst Haussecker, Patrick Cheung, Monitoring and Fault Diagnosis of Hybrid Systems [J],IEEE Transactions on Systems, Man, and Cybernetics—Part B: Cybernetics, 2005, 35( 6): 1225-1240
[19] S L Chen, R J K Wood, L Wang, R Callan , H E G Powrie, Wear detection of rolling element bearings using multiple-sensing technologies and mixture-model-based clustering method[C],Proc. IMechE 2008, Vol.222 Part O:J. Risk and Reliability: 207-218
[20] Paolo Pennacchi, NicolòBachschmid, Andrea Vania, Gian Antonio Zanetta and Luca Gregori , Use of modal representation for the supporting structure in model based fault identification of large rotating machinery: part 1—theoretical remarks[J], Mechanical Systems and Signal Processing, 2006, 20(3): 662-681
[21] Christof Devriendt, Gert De Sitter, Steve Vanlanduit, Patrick Guillaume, Operational modal analysis in the presence of harmonic excitations by the use of transmissibility measurements[J],Mechanical Systems and Signal Processing, 2009, 23( 3): 621-635
[22] E. Pierro, E. Mucchi, L. Soria, A. Vecchio, On the vibro-acoustical operational modal analysis of a helicopter cabin[J],Mechanical Systems and Signal Processing, 2009,23(4): 1205-1217
[23] Christof Devriendt, Gert De Sitter, Steve Vanlanduit, Patrick Guillaume, Operational modal analysis in the presence of harmonic excitations by the use of transmissibility measurements[J],Mechanical Systems and Signal Processing, 2009,23(3):.621-635
[24] R. Pintelon, B. Peeters, P. Guillaume, Continuous-time operational modal analysis in the presence of harmonic disturbances[J],Mechanical Systems and Signal Processing, 2008, 22(5): 1017-1035
[25] R. Pintelon and J. Schoukens, System Identification: A Frequency Domain Approach[M], IEEE Press, Piscataway (2001)
[26] B. Peeters, G. Lowet, H. Van Der Auweraer and J. Leuridan, A new procedure for modal parameter estimation[J], Sound and Vibration ,2004,38 (1) : 24–29
[27] B. Peeters, H. Van Der Auweraer, P. Guillaume and J. Leuridan, The polymax frequency-domain method: a new standard for modal parameter estimation[J], Shock and Vibration ,2004,11 (3–4) : 395–409
[28]熊诗波,王然风,梁义维,轧机自激振动诊断和结构动力学修改[J],机械工程学报,2005, 41(7): 147-151
[29] D. Hanson, R.B. Randall, J. Antoni, D.J. Thompson, T.P. Waters and R.A.J. Ford , Cyclostationarity and the cepstrum for operational modal analysis of mimo systems—Part I: Modal parameter identification[J] , Mechanical Systems and Signal Processing, 2007, 21(6): 2441-2458.
[30] Ljung L, Convergence Analysis of Paramet ric Identification Methods. IEEE Trans. on Automatic Control ,1978 ,AC- 23 :770 - 783.
[31]徐小平,王峰,胡钢,系统辨识研究的现状[J],现代电子技术,2007, 30(15):112-116
[32]段丽玮,吴志华,徐志伟,基于ARX模型的飞机尾翼压电结构系统辨识研究[J],压电与声光, 2008,30(6):760-762
[33]李秀英,韩志刚,非线性系统辨识方法的新进展[J],自动化技术与应用,2004,23(10):5-7
[34]朱豫才,过程控制的多变量系统辨识[M],国防科技大学出版社,湖南,2005
[35]朱燕飞,谭洪舟,章云,一类非线性系统盲辨识算法及仿真研究[J],系统仿真学报,2008,20(14):3782-3784
[36]侯媛彬,系统辨识及其MATLAB仿真[M],科学出版社,北京,2004
[37]於东军,郑宇杰,吴小俊,杨静宇,基于Kernel-SOM的非线性系统辨识及模型运行收敛性分析[J],电子与信息学报,2008,30(8):1928-1931
[38]徐祖华,赵均,钱积新,基于操作轨迹LPV模型的非线性辨识[J],系统工程理论与实践,2008,28(7):155-159
[39]胡钋,具有维纳-哈默斯坦模型结构非线性系统的一种辨识方法[J],电子学报,2009,(9):1907-1911
[40]庞世伟,于开平,邹经湘,利用NARMA模型辨识非线性时变结构系统[J],哈尔滨工业大学学报, 2008,40(1):12-16
[41]张恒,李积德,赵晓东,基于系统辨识方法求解船舶非线性运动响应[J],大连海事大学学报,2008,34(4):67-71
[42]王宏伟,马广富,王子才,模糊辨识理论与应用研究发展[J],系统仿真学报,2000,12(2): 87-126
[43]王士同,於东军,非线性系统的模糊辨识误差分析,软件学报[J],2000,11(4):447-452
[44]王然风,基于支持向量回归技术的大型复杂机电设备故障诊断研究与应用[D],博士学位论文,2005
[45] Takagi T , Sugeno M. Fuzzy Identification of Systems and Its Application to Modeling and Cont rol. IEEE Trans.on Systems ,Man and Cybernetics [J],1985 ,15 (1) :116 - 132.
[46] Johansen T A ,Murray - Smith R. On the Interpretation and Identification of Dynamic Takagi - Sugeno Fuzzy Models [J ] . IEEE Trans. on Fuzzy Systems , 2000 , 8 (3) : 297- 313.
[47] Leec H , Tengc C. Identification and Cont rol of DynamicSystems Using Recurrent Fuzzy Network [ J ] . IEEE Trans. on Fuzzy Systems ,2000 ,8 (4) :349 - 366.
[48]李人厚,张平安,关于模糊辨识的理论与应用实际问题,控制理论与应用[J], 1995,12 (2):129 - 137
[49]邵青,冯汝鹏,非线性系统模糊辨识的新方法[J],控制与决策,2001 ,16(1) :83 - 85
[50]刘福才,关新平,裴润,基于一种新模糊模型的非线性系统模糊辨识[J],控制理论与应用, 2003 ,20(1) :113 - 116
[51]李娟,模糊辨识方法研究进展[J],莱阳农学院学报,(17)1:71-76
[52] Y. F. Wang, D. H. Wang, T. Y. Chai. Modeling and control compensation of nonlinear friction using adaptive fuzzy systems [J]. Mechanical Systems and Signal Processing, 2009, 23: 2445-2457
[53]李超顺,周建中,安学利,向秀桥,李清清,基于T_S模糊模型的水轮机调节系统辨识[J].武汉大学学报(工学版),2010,43(1):108-111
[54]赵志刚,吕恬生,王庚,基于Takagi-Sugen模糊模型的小型无人直升机系统辨识[J],上海交通大学学报,2008,42(5):856-859
[55]王广军,王志杰,陈红,基于递阶分解聚类的非线性系统递推模糊辨识[J],控制与决策,2009, 24(12):1846-1850
[56]于龙,肖建,白裔峰,基于批量模糊学习矢量量化的模糊系统辨识[J],控制与决策,2007,22(8),903-906
[57]易继锴,侯媛彬.智能控制技术[M].北京:北京工业大学出版社,1999
[58]李茶玲,孙德保,遗传算法在系统辨识中的应用[J ] ,华中理工大学学报,1998 ,26 (7) :57 - 58
[59]王晓鹏,万敏,一种基于遗传算法的动力学系统辨识方法[J],飞行力学,2003,21(2):56-58
[60]姜波,江秉文,基于遗传算法的非线性系统模型参数估计[J],控制理论与应用, 2000, 17 (1) :150 - 152
[61]边润强,陈增强,袁著祉,一种改进的遗传算法及其在系统辨识中的应用[J],控制与决策, 2000 ,15(5) :623 - 625
[62]徐洪泽,一种具有变异性杂交的遗传算法及其在系统辨识中的应用[J],哈尔滨工业大学学报,1997 ,29(4) :74 - 75
[63]蒙祖强,蔡自兴,一种基于并行遗传算法非线性系统辨识方法[J],控制与决策. 2003 ,18 (3) :367– 374
[64]吴茂林,黄声华,永磁同步电机非线性参数辨识[J].电工技术学报,2009,24(8):65-68
[65]商秀芹,卢建刚,孙优贤,改进遗传规划算法在系统辨识中的应用[J],东南大学学报(自然科学版),2009,39(Sup(I)):22-26
[66]龚固丰,章兢,何敏,王炼红,混合编码免疫算法在非线性系统辨识中的应用[J],系统仿真学报,2009,21(12):3561-3564
[67]徐小平,钱富才,刘丁,王峰,基于PSO算法的系统辨识方法[J].系统仿真学报,2008,20(13):3525-3528
[68]赵宝江,李士勇,基于蚁群聚类算法的非线性系统辨识[J],控制与决策,2007,(10):1193-1200
[69]翟永杰,尚雪莲,韩璞等,SVR在传感器故障诊断中的仿真研究[J],系统仿真学报,2004, 16( 6):1257-1279
[70]马勇,黄德先,金以慧,基于支持向量机的软测量建模方法[J],信息与控制,2004,33(4): 417-421
[71] J A K. Suykens,Nonlinear modeling and support vector machines[C],Proc of the 18th IEEE Conf on Instrumentation and Measurement Technology .Budapest,2001:287-294
[72]黄宴委,吴惕华,赵静一,回归型支持向量机的系统辨识及仿真[J],计算机仿真,2004,21(5): 41-44
[73] J A K Suykens,Least squares support vector machines for classification and nonlinear modelling,Neural Network World,2000,10 (1～2) :29～48
[74]蔡艳宁,胡昌华,辨识非线性MIMO系统的多输出ε-SVR模型研究[J].控制与决策,2008,23(7):813-816
[75]魏东,张明廉,基于神经网络的非线性模型辨识[J],北京建筑工程学院学报,2004,20(4):26-30
[76]苑希民,崔广涛,张玉峰,流激振动系统的神经网络辨识和预报[J],水利学报,1999,(3):13-20
[77]李保奎,神经网络辨识方法及其在轧钢控制中的应用[J],北京理工大学学报, 2002,22(3): 311-314
[78]刘国栋,用神经网络辨识非线性大滞后系统的研究[J],信息与控制,2000, 29(3):225-229
[79]饶文碧,程洪斌,方复兴,结构损伤神经网络辨识系统的实现[J],武汉理工大学学报, 2002, 24(1):28-30
[80] Vicky Rouss, Willy Charon, Giansalvo Cirrincione. Neural model of the dynamic behavior of a non-linear mechanical system[J]. Mechanical Systems and Signal Processing, 2009, 23:1145-1159
[81] Leandro dos Santos Coelho, Marcelo Wicthoff Pesso? a. Nonlinear identification using a B-spline neural network and chaotic immune approaches[J]. Mechanical Systems and Signal Processing, 2009, 23: 2418-2434
[82]吴德会.非线性动态系统的Wiener神经网络辨识法[J].控制理论与应用,2009,26(11):1192-1196
[83]于开平,董好志.基于前向神经网络的时变非线性结构系统辨识快速递推最小二乘法[J].振动工程学报,2007,20(5):468-472
[84]陈华伟,钟化兰,靳蕃.基于双向权值调整算法的神经网络非线性系统辨识[J].铁道学报,2007,10(5):48-53
[85]陈涵,邓长虹,李大路.基于循环神经网络的动态等值模型辨识[J].高电压技术,2008,34(5):1001-1004
[86]奚海蛟,张晓林.基于Elman网络的共轴式直升机动力学系统辨识[J].北京航空航天大学学报,2008,34(7):861-864
[87]岑豫皖,叶金杰,潘紫微.非线性状态空间方法辨识电液伺服控制系统[J].机械工程学报,2008,44(12):80-85
[88]刘益剑,方彦军,马宝萍.滑动数据窗口驱动的贝叶斯-高斯网络及其在非线性系统辨识中的应用[J].控制理论与应用,2009,26(12):1435-1438
[89]胡玉玲,曹建国.基于模糊神经网络的动态非线性系统辨识研究[J].系统仿真学报,2007,19(3):560-562
[90]刘胜,赵红.遗传算法—模糊聚类动态模糊神经网络辨识[J].哈尔滨工程大学学报,2008,29(8):825-830
[91]葛宏伟,李小琳,梁艳春,何湘东.基于免疫粒子群优化的一种动态递归神经网络辨识与控制非线性系统[J].吉林大学学报(工学版),2008,38(4):858-864
[92]刘本德,胡昌华.基于Volterra频域核辨识的非线性模拟电路故障诊断[J].控制与决策,2009,24(8):1167-1171
[93]张贤达,现代信号处理[M],北京大学出版社,2002
[94]陈仲生,基于MATLAB7.0的统计信息处理[M],湖南科学技术出版社,2005
[95] John G.Proakis等著,汤俊等译,统计信号处理算法[M],清华大学出版社.2006.3:500～506
[96]苏文斌,温熙森,史维祥,故障诊断中非线性耦合特征提取的研究[J],西安交通大学学报, 1999,33(1)
[97]韩敏,混沌时间序列预测理论与方法[M],中国水利水电出版社,2007,5
[98]王鼐,非线性动力学方法在时间序列分析中的应用[D],复旦大学博士论文,2005
[99]刘秉正,彭建华,非线性动力学[M],高等教育出版社,2004.
[100]朱明武,李永新,卜雄洙,测试信号处理与分析[M],北京航空航天大学出版社2006
[101]佟德纯,姚宝恒,工程信号处理与设备诊断[M],科学出版社,2008
[102]张善文,雷英杰,冯有前,MATLAB在时间序列分析中的应用[M],西安电子科技大学出版社,2007
[103] Andrew R.Webb著,王萍,杨培龙,罗颖昕译,统计模式识别[M],电子工业出版社2004
[104]温熙森,模式识别与状态监控[M],科学出版社,2007
[105]张志武,孙新娟,刘雪梅.利用自组织特征映射神经网络实现数据分区[J].数据库与信息处理,2007,10:130-132
[106]齐志.基于SOM神经网络的聚类可视化方法研究[D].东北师范大学硕士学位论文,2009
[107]王莉,王正欧.TGSOM:一种用于数据聚类的动态自组织映射神经网络[J].电子与信息学报,2003,25(3):313-319
[108]闻新,周露等.MATLAB神经网络仿真与应用[M].北京:科学出版社,2006
[109]周建新,罗晓玲,付传秀.自组织特征映射神经网络的区域经济发展聚类分析[J].贵州大学学报(自然科学版),2008,25(2):127-130
[110]倪步喜,章丽芙,姚敏.基于SOFM网络的聚类分析[J].计算机工程与设计,2006,27(5):855-857
[111]李戈,邵峰晶,朱本浩.基于神经网络聚类的研究[J].青岛大学学报,2001,16(4):1-4
[112] Johnson R A, Wichern D W.实用多元统计分析(第四版)[M].陆璇,葛余博,赵衡秀等译,清华大学出版社,2001
[113]朱永生,实验数据多元统计分析[M],科学出版社,2009
[114]张杰.多变量统计过程控制[M].北京:化学工业出版社,2000.
[115]齐晓慧等,现代控制理论及应用[M],国防工业出版社,2007
[116]魏东,非线性系统神经网络参数预测及控制,机械工业出版社, 2008:29-31
[117] Norgaard,M. (2000). Neural network based system identification toolbox.Technical Report. 00-E-891, Department of Automation, Technical University of Denmark.
[118]张代远,神经网络新理论与方法[M],清华大学出版社,2006
[119]熊晓燕,高分辨率扭振测量方法及其应用[J],振动、测试与诊断,2003,23(1)
[120]唐向宏,李齐良,时频分析与小波变换[M],科学出版社,2008
[121]陈恩伟,机器人动态特性及动力学参数辨识研究[M],合肥工业大学出版社,2008
[122]曹建福,韩崇昭,方洋旺,非线性系统理论及应用[M],西安交通大学出版社,2006
[123] J.C. Peyton Jones,Simplified computation of the Volterra frequency response functions of non-linear systems,Mechanical Systems and Signal Processing 21 (2007): 1452–1468