商用车变速器疲劳实验特征辨识与寿命预测
|
摘要
变速器作为车辆传动系统的关键部件,起着改变汽车驱动力和车速的作用。随着汽车产业的快速增长,变速器呈现了系列化、模块化、轻量化的发展趋势,这对变速器快速设计和生产提出了更高要求。在保证变速器可靠性前提下,为了进一步加快新品的研发,有必要对变速器疲劳寿命试验方法进行改进以缩短研发周期。变速器作为复杂系统,从系统角度出发结合零部件疲劳状况进行分析成为一个新的研究方向,此外,在实际生产中,传统的时频分析方法应用效果欠佳,不能较好满足实际生产中对疲劳测试信号的动态分析和监控的需要。因此,本文基于疲劳寿命预测理论、机器学习理论和振动信号分析方法,在大量变速器疲劳寿命试验基础上对变速器疲劳寿命试验方法进行改进、对变速器疲劳状态进行特征辨识、并对变速器各档寿命进行了预测,对掌握试验变速器疲劳寿命状态特性具有理论和实践意义。论文主要研究内容如下：
1)对变速器总成进行了有限元仿真和模态试验分析,得到了变速器低阶固有频率及振型,通过对比理论和试验数据验证了模态参数识别的可信性并确定了变速器薄弱环节,为疲劳试验提供了依据。基于疲劳损伤累积理论,分析了变速器载荷谱、应力循环次数的关系以及关键零件在不同载荷强化系数作用下的损伤度,提出了“删低强高”的变速器加速疲劳试验方法；与等幅疲劳方法对比得到了等幅疲劳、加速疲劳这两种试验方法关于循环次数、损伤度的当量关系；通过对比试验验证了这种加速疲劳试验方法保持了失效机理的正确性。
2)完成了三轴式、双中间轴式、行星轮式三种变速器疲劳寿命试验和振动信号测试,建立了基于峭度、均方幅值指标与采样点次数(循环次数)关系的变速器疲劳寿命曲线；结合变速器试验工况以及疲劳失效状况,分析了各变速器关键档位疲劳寿命曲线的变化趋势,并得出双中间轴式变速器的抗振动冲击性优于三轴式和行星轮系变速器的结论。
3)基于循环平稳理论、独立分量分析法和支持向量机分类法,提出了针对同类传动结构、不同载荷的变速器疲劳状态进行特征辨识的综合分析方法；分别以峭度、峭度绝对值、峭度平方作为特征量,采用一对一、一对多、直接构造多分类器的支持向量机分类方法,对三类变速器疲劳寿命试验数据进行特征提取和辨识,验证了这种方法的合理性。
4)建立了齿轮—轴—轴承的变速器动态仿真模型,分析了循环周期内动态接触应力和弯曲应力变化；基于疲劳损伤理论和非线性临界平面有限元分析法,快速预测各齿轮的疲劳累积损伤区域；考虑了变速器齿轮疲劳寿命主要影响因素对材料S-N疲劳寿命曲线进行修正,提高了预测的准确性；通过对比疲劳寿命仿真与试验结果验证了这种方法。
5)提出了基于模糊支持向量机回归的变速器疲劳寿命预测方法,建立了变速器应力循环累积因素和温度变化因素影响的核函数,实现了对试验变速器的各档齿轮进行寿命的预测；通过对三类变速器的各档疲劳寿命的试验值与预测值比较验证了这种方法。
Transmission, as one of vehicle transmission system key components, plays a crucial role on the automobile driving force and speed. As the fast growth of automobile industry, this thesis describes the present status of transmission, and that is serialization, combination and lightweight. Then, it is necessary to put forward the requirements of transmission rapid design and production. In the conditions of assuring transmission reliability, to accelerate the development of new products further, exploring new ways of transmission fatigue life test is of great necessity. Transmission, as a complex system, from system perspective, analyzing combined with parts fatigue condition, has become a new direction. What is more, in practical production, the present effect of traditional time-frequency analysis method is far from perfect. Therefore, it has not been able to satisfy the need of signal dynamic analysis and monitoring in fatigue test. So, on the basis of the fatigue life prediction theory, the statistics analysis theory and vibration signal fault theory, transmission fatigue condition and life prediction are analyzed in this thesis. It is of significance in theory and practice to master transmission fatigue life dynamic characteristics.The main research contents of this thesis are roughly as follows.
1) Through condutng finite element simulation analysis and modal test analysis, the low order natural frequencies and corresponding modes of transmission assembly are extracted. The test data is coincided with analytical results, which indicates the reliability of modal parameters. Modal analysis shows the weak position of transmission, which provides a basis for fatigue test. In view of the fatigue damage cumulative theory, by analyzing the relationship between transmission load spectrum and stress cycle times, and the damage degree of key parts with different load strengthen coefficient, a accelerating fatigue test method is put forward. With constant amplitude fatigue contrast test methods, under two test methods, constant amplitude fatigue test method and accelerated fatigue test method, the equivalent relationship of cycle time and damage degree is determined. It can be easily verified that accelerated fatigue test methods keep the correctness of the failure mechanism through contrast test.
2) For three series transmissions, concluding triaxial transmission, double countershaft transmission and planetary gear train transmission, fatigue life dynamic test and vibration signal test are conducted. And transmissions fatigue life curve, which is based on kurtosis, mean square amplitude index and sample point number, is established. Combined with transmission fatigue invalidation condition, through analyzing key gear fatigue life curve changes of each transmission, it can be concluded that anti-vibration and impact performance of double countershaft transmission is superior to that of triaxial transmission and planetary gear train transmission.
3) On account of cyclostationarity theory, independent component analysis and support vector machine classification, this thesis puts forward comprehensive analysis method for pattern recognition, which is aiming mainly at studying transmission fatigue state, and this kind transmission consist similar transmission structure,but different load. Kurtosis, kurtosis absolute value and kurtosis square are regarded respectively as independent component. By using the classification methods of support vector machine, which include one-to-one, one-to-many and direct constructing multi-class classification support vector classifier, this thesis deals with fatigue life test data of three kinds transmission, and conducts feature extraction and recognition for these data. The testl results show that the test method is correct.
4) A dynamic simulation model of gear-shaft-bearing transmission system is established. Then, the dynamic contact stress and the bending stress variation of gear system are analyzed throughout the cycle. Based on the fatigue damage theory and nonlinear critical plane finite element analysis method, transmission fatigue life of every gear is obtained.Taking into consideration the main factors that influence transmission gear fatigue life, material S-N curve is modified in this thesis, and the accuracy of forecast are improved, and fatigue damage cumulative failure area of each gear is forecasted quickly.
5) On the basis of fuzzy support vector machine regression theory, kernel function, which is influenced by transmission stress cycle accumulation factor and temperature variation factor, is proposed with transmission fatigue life prediction method. Residual life forecast is realized for every gear of transmission, and the feasibility of the technique is proved through comparing predicted valuel with test value of three kinds of transmission fatigue life.
1)对变速器总成进行了有限元仿真和模态试验分析,得到了变速器低阶固有频率及振型,通过对比理论和试验数据验证了模态参数识别的可信性并确定了变速器薄弱环节,为疲劳试验提供了依据。基于疲劳损伤累积理论,分析了变速器载荷谱、应力循环次数的关系以及关键零件在不同载荷强化系数作用下的损伤度,提出了“删低强高”的变速器加速疲劳试验方法；与等幅疲劳方法对比得到了等幅疲劳、加速疲劳这两种试验方法关于循环次数、损伤度的当量关系；通过对比试验验证了这种加速疲劳试验方法保持了失效机理的正确性。
2)完成了三轴式、双中间轴式、行星轮式三种变速器疲劳寿命试验和振动信号测试,建立了基于峭度、均方幅值指标与采样点次数(循环次数)关系的变速器疲劳寿命曲线；结合变速器试验工况以及疲劳失效状况,分析了各变速器关键档位疲劳寿命曲线的变化趋势,并得出双中间轴式变速器的抗振动冲击性优于三轴式和行星轮系变速器的结论。
3)基于循环平稳理论、独立分量分析法和支持向量机分类法,提出了针对同类传动结构、不同载荷的变速器疲劳状态进行特征辨识的综合分析方法；分别以峭度、峭度绝对值、峭度平方作为特征量,采用一对一、一对多、直接构造多分类器的支持向量机分类方法,对三类变速器疲劳寿命试验数据进行特征提取和辨识,验证了这种方法的合理性。
4)建立了齿轮—轴—轴承的变速器动态仿真模型,分析了循环周期内动态接触应力和弯曲应力变化；基于疲劳损伤理论和非线性临界平面有限元分析法,快速预测各齿轮的疲劳累积损伤区域；考虑了变速器齿轮疲劳寿命主要影响因素对材料S-N疲劳寿命曲线进行修正,提高了预测的准确性；通过对比疲劳寿命仿真与试验结果验证了这种方法。
5)提出了基于模糊支持向量机回归的变速器疲劳寿命预测方法,建立了变速器应力循环累积因素和温度变化因素影响的核函数,实现了对试验变速器的各档齿轮进行寿命的预测；通过对三类变速器的各档疲劳寿命的试验值与预测值比较验证了这种方法。
Transmission, as one of vehicle transmission system key components, plays a crucial role on the automobile driving force and speed. As the fast growth of automobile industry, this thesis describes the present status of transmission, and that is serialization, combination and lightweight. Then, it is necessary to put forward the requirements of transmission rapid design and production. In the conditions of assuring transmission reliability, to accelerate the development of new products further, exploring new ways of transmission fatigue life test is of great necessity. Transmission, as a complex system, from system perspective, analyzing combined with parts fatigue condition, has become a new direction. What is more, in practical production, the present effect of traditional time-frequency analysis method is far from perfect. Therefore, it has not been able to satisfy the need of signal dynamic analysis and monitoring in fatigue test. So, on the basis of the fatigue life prediction theory, the statistics analysis theory and vibration signal fault theory, transmission fatigue condition and life prediction are analyzed in this thesis. It is of significance in theory and practice to master transmission fatigue life dynamic characteristics.The main research contents of this thesis are roughly as follows.
1) Through condutng finite element simulation analysis and modal test analysis, the low order natural frequencies and corresponding modes of transmission assembly are extracted. The test data is coincided with analytical results, which indicates the reliability of modal parameters. Modal analysis shows the weak position of transmission, which provides a basis for fatigue test. In view of the fatigue damage cumulative theory, by analyzing the relationship between transmission load spectrum and stress cycle times, and the damage degree of key parts with different load strengthen coefficient, a accelerating fatigue test method is put forward. With constant amplitude fatigue contrast test methods, under two test methods, constant amplitude fatigue test method and accelerated fatigue test method, the equivalent relationship of cycle time and damage degree is determined. It can be easily verified that accelerated fatigue test methods keep the correctness of the failure mechanism through contrast test.
2) For three series transmissions, concluding triaxial transmission, double countershaft transmission and planetary gear train transmission, fatigue life dynamic test and vibration signal test are conducted. And transmissions fatigue life curve, which is based on kurtosis, mean square amplitude index and sample point number, is established. Combined with transmission fatigue invalidation condition, through analyzing key gear fatigue life curve changes of each transmission, it can be concluded that anti-vibration and impact performance of double countershaft transmission is superior to that of triaxial transmission and planetary gear train transmission.
3) On account of cyclostationarity theory, independent component analysis and support vector machine classification, this thesis puts forward comprehensive analysis method for pattern recognition, which is aiming mainly at studying transmission fatigue state, and this kind transmission consist similar transmission structure,but different load. Kurtosis, kurtosis absolute value and kurtosis square are regarded respectively as independent component. By using the classification methods of support vector machine, which include one-to-one, one-to-many and direct constructing multi-class classification support vector classifier, this thesis deals with fatigue life test data of three kinds transmission, and conducts feature extraction and recognition for these data. The testl results show that the test method is correct.
4) A dynamic simulation model of gear-shaft-bearing transmission system is established. Then, the dynamic contact stress and the bending stress variation of gear system are analyzed throughout the cycle. Based on the fatigue damage theory and nonlinear critical plane finite element analysis method, transmission fatigue life of every gear is obtained.Taking into consideration the main factors that influence transmission gear fatigue life, material S-N curve is modified in this thesis, and the accuracy of forecast are improved, and fatigue damage cumulative failure area of each gear is forecasted quickly.
5) On the basis of fuzzy support vector machine regression theory, kernel function, which is influenced by transmission stress cycle accumulation factor and temperature variation factor, is proposed with transmission fatigue life prediction method. Residual life forecast is realized for every gear of transmission, and the feasibility of the technique is proved through comparing predicted valuel with test value of three kinds of transmission fatigue life.
引文
[1]吴修义.机械变速器系列化及其与车辆的匹配[J].重型汽车,2004(1)：14-15.
[2]Wang Tie,Shen Jun,Zhao Fuqiang.Modular design on basic parameters of volume reducer[C].Applied Mechanics and Materials.2011,vol.86:633-636.
[3]刘义伦.工程构件疲劳寿命预测理论与方法[M].湖南科学技术出版社,1997：3-3.
[4]袁熙,李舜酩.疲劳寿命预测方法的研究现状与发展[J].航空制造技术,2005(12)：80-84.
[5]Galietti UMorabito, Annaeva E.Energy-analysis of fatigue damage by thermographic technique.Proceedings of SPIE-The International Society for Optical Engineering, Orlando, vol.4,2002:456-463.
[6]姚磊江,童小燕,吕胜利.关于疲劳劳能量理论若干问题的讨论[J].机械强度,2004(26)：278-281.
[7]Jiang M X, Yong C Z.Dynamic modeling of degradation data[C].IEEE Proceedings Annual Reliability and Maintain-ability Symposium,2002:607-610.
[8]Atzori B, Lazzarin P, Meneghetti G.Fracture mechanics and notch sensitivity[J]. Fatigue and Fractureof Engineering Material and Structures,2003,26(3):257-267.
[9]Verreman Y, Limodin N.Fatigue notch factor and short crack propagation[J]. Engineering Fracture Me-chanics,2008,75(6):1320-1335.
[10]Atzori B, Meneghetti G, Susmel L.Fatigue behav-iour AA356-T6 cast aluminium alloy weakened bycracks and notches[J]. Engineering Fracture Mechan-ics,2004,71(4-6):759-768.
[11]Repetto M P Cycle counting methods for bi-modal stationary Gaussian processes[J]. Probabilistic Engineering Mechanics,2005(20):229-238.
[12]M.Grigoriu.A spectral representation based modal for Monte Carlo simulation[J]. Probabilistic Engineering Mechanics,2000,15:365-370.
[13]Chapetti M D.Fatigue propagation threshold of short cracks under constant amplitude loading[J]. International Journal of Fatigue,2003,25(12):1319-1326.
[14]Forth S C, Newman J C, Forman R G.On generating fatigue crack growth thresholds[J]. International Journal of Fatigue,2003,25(1):9-15.
[15]Beretta S, Carboni M, Madia M.Modelling of fatigue thresholds for small cracks in a mild steel by"Strip-Yield"model[J]. Engineering Fracture Mechanics,2009,76(10):1548-1561.
[16]冯胜,程燕平,赵亚丽等.线性疲劳劳损伤累积理论的研究[J].哈尔滨工业大学学报,2003(5)：608-610.
[17]贡金鑫,王海超,赵国藩.结构疲劳累积损伤与极限承载能力可靠度[J].大连理工大学学报,2002(6)：714-717.
[18]姚磊江.疲劳过程中的能量耗散分析及基于能量耗散的疲劳损伤模型[D].陕西：西安西北工业大学,2004.
[19]侯善芹,许金泉.基于疲劳特征长度概念的-种新疲劳理论[J].上海交通大学学报,2010(10)：1443-1448.
[20]沈海军,郭万林,冯谦.材料S-N、ε-N及da/dN-ΔK疲劳性能数据之间的内在联系[J].机械强度2003(5)：556-560.
[21]叶笃毅,王德俊,童小燕等.一种基于材料韧性耗散分析的疲劳损伤定量新方法[J].实验力学,1999(1)：80-88.
[22]Orchard M E. A Particle Filtering-based Framework for On-line Fault Diagnosis and Failure Prognosis[D]. Georgia:Georgia Institute of Technology,2006.
[23]Marcos E,et al. A novel RSPF approach to prediction to prediction of high-risk,low-probability failure event[C] Annual Conference of the Prognostics and Health Management Society,2009.
[24]Chelidze D,et al. A dynamical systems approach to damage evolution tracking part 1 description and experimental application[J]Journal of Vibration and Acoustics,2002(124):250-257.
[25]滕红智,赵建民,贾希胜等.基于状态空间模型的齿轮磨损预测研究[J].机械科学与技术,2011(12)：2086-2091.
[26]王秋景,管迪华.汽车零部件加速疲劳试验方法[J].汽车技术,1997,11(1)：14-17.
[27]XIONG J J, SHENOI R A.A load history generation approach for full-scale accelerated fatigue tests[J]Engineering Fracture Mechanics,2008,75(12):3226-3243.
[28]RAJU P R, SATYANARAYANA B B, BABU K S.Evaluation of fatigue life of aluminum alloy wheels under radial loads[J]Engineering Failure Analysis 2007,14(4):791-800.
[29]PALIN-LUC T, BANVILLET A, VITTORI J P.How to reduce the duration of multiaxial fatigue tests under proportional service load[J]International Journal of Fatigue 2006,28(4):554-563.
[30]王秋景.工程疲劳寿命估算及对汽车前后轴疲劳试验方法的评价[D].北京：消华大学,1996.
[31]李国云,秦大同.风力发电机齿轮箱加速疲劳试验技术分析[J].重庆大学学报,2009(11)：1253-1255.
[32]卢曦,郑松林.轿车主减速器齿轮疲劳寿命的试验研究[J].机械强度,2008(4)：664-667.
[33]蒋荟.加速疲劳劳试验谱块的高载循环丢失问题及其解决方法[JJ.机械工程学报,2010(5)：194-197.
[34]张洪才,黄克正,陈举华等.秋基于断裂力学理论的表面淬火齿轮疲劳劳寿命的数值计算[J].应用力学学报,2004(3)：17-21.
[35]陈东升,钟其水,陈欣.车辆变速箱齿轮弯曲疲劳寿命的估算[J].机械设计,2002(5)：36-40.
[36]王小群,边新孝,邱丽芳等.40MnB调质齿轮弯曲疲劳强度的试验研究[J].机械传动,2003(2)：51-53.
[37]张君彩,边新孝,郑文林等35SIMn调质齿轮弯曲疲劳强度的试验研究[J].河北科技大学学报,2003(3)：63-66.
[38]武志斐,王铁,张瑞亮18Cr2Ni4WA齿轮接触疲劳特性试验研究[J].兵工学报,2010(5)：598-602.
[39]李红梅,王铁,张瑞亮.齿轮接触疲劳极限应力快速测定法的应用[J].机械传动,2010(5)：95-98.
[40]赵富强,于铁42CrMo钢渗碳淬火齿轮弯曲疲劳极限快速测定[J].机械设计与研究,2011(4)：77-79.
[41]Wang Tie, Li Hongmei, Zhang Ruiliang, et al Research on gear contact fatigue stress test[C].Applied Mechanics and Materials,2011(86):825-828.
[42]祁倩,王永,刘世军等42CrMo调质及表面淬火渐开线齿轮弯曲疲劳强度试验[J].机械传动,2010(9)：69-71.
[43]王国军,闫清东,项昌乐等18Cr2Ni4WA渗碳淬火齿轮弯曲疲劳特性试验研究[J].机械传动,2006(5)：46-59.
[44]尚德广,王德俊.多轴疲劳劳强度[M].北京：科学出版社,2007.
[45]Carpinteri A, Spagnoli A.Multiaxial high-cycle fatigue criterion for hard metals[J]. International Journal of Fatigue,2001(23):135-145.
[46]Spagnoli A. A new high-cycle fatigue criterion applied to out-of-phase biaxial stress state[J]. International Journal of Mechanical Sciences 2001(43):2581-2595.
[47]Wang YY, Yao WX.Evaluation and comparison of several multiaxial fatigue criteria[J].International Journal of Fatigue,2004,26(1):17-25
[48]Farahani AV. A new energy critical plane parameter for fatigue life assessment of various metallic materials subjected to in-phase and out-of-phase multiaxial fatigue loading conditions[J]. International Journal of Fatigue 2000(22):295-305.
[49]于海生,谢.尼.舒卡耶夫,王兴国等.一种多轴非比例载荷低周疲劳寿命预测方法[J].机械强度,2004(S1)：250-253.
[50]尚德广,王大谦,孙国芹等.多轴疲劳裂纹扩展行为研究[J].机械强度,2004,26(4)：423-427.
[51]Benedetti M., Fontanari V., Hohn B.R. Influence of shot peening on bending tooth fatigue limit of casehardened gears[J]. International Journal of Fatigue,2002(24):1127-1136.
[52]Glodez S., M.Sraml, J.Kramberger. A computational model for determination of service life of gears[J]International Journal of Fatigue,2002,24(10):1013-1020.
[53]J.Kramberger, M.raml, I.Potro.Numerical calculation of bending fatigue life of thin-rim spur gears[J]Engineering Fracture Mechanics,2004(71):647-656.
[54]E.Akata, M.T.Altmbalik, Y.Can.Three point load application in single tooth bending fatigue test for evaluation of gear blank manufacturing methods[J] International journal of Fatigue,2004,26(7):785-789.
[55]G. Fajdiga, M.Sraml. Fatigue crack initiation and propagation under cyclic contact loading[J]. Engineering Fracture Mechanics,2009(9):1320-1335.
[56]章文强,盛云等.燃料电池轿车变速器齿轮强度分析及疲劳寿命计算[J].传动技术,2009(3)：23-47.
[57]Akpan U O, Rushton P A and Koko S T.Development of a fuzzy probabilistic methodology for multiple-site fatigue damage[J]. Journal of aircraft,2004,41(3):633-640.
[58]张玉瑞,陈剑波.基于RBF神经网络的时间序列预测[J].计算机工程与应用用,2005(11)：74-76.
[59]张嵩,汪元美.基于广义径向基函数神经网络的非非线性时间序列预测器[J].电子科学学刊,2000(6)：965-971.
[60]王丽娜.渐开线齿轮传动疲劳寿命分析[D].山西：太原理工大学,2009.
[61]邓乃扬,田英杰.支持向量机-理论、算法与拓展[M].北京：科学出版社,2009.
[62]VapnikVN.Statistical Learning Theory[M]Newyork, Springer,1998.
[63]Suykens J.A.K.,Vandewalle J.,Moor D.B. OPtimal Control by Least squares Support Vector Maehines[J]. Neural Networks,2001.14(1):23-35.
[64]Platt J. Fast training of support vector machines using sequential minimal optimization [C].Scholkopf B, Burges C., Smola A.Advances in KernelMethods-Support Vector Learning.Cambridge:MIT Press, 1999:185-208.
[65]Platt J.using analytic QP and sparseness to speed training f support vectormachines [C].KearnsM, Solla S, CohnD. Advances in Neural Information Processing Systems. Cambridge:MIT Press,1999:557-563.
[66]Francis E.Htay, Cao L J. Application of support vector machines in financial time series forecasting[J]Omega,2001(29):309-317.
[67]朱家元,段宝君,张恒喜.新型SVM对时间序列预测研究[J].计算机科学,2003(8)：124-125.
[68]奉国,朱思铭.改进SVM及其在时间序列数据预测中的应用[J].华南理工大学学报,2005(5)：19-22.
[69]江田汉,束炯.基于LSSVM的混沌时间序列的多步预测[J].控制与决策,2006(1)：77-80.
[70]Suykens J A K,Gestel T V,Brahanter J D,et al. Least Squares Support Vector Machines[M].River Edge: World Scientific,2002:71-148.
[71]王旭亮.不确定性疲劳寿命预测方法研究[D].江苏：南京航空航天大学,2009.
[72]Akpan U O, Rushton P A and Koko S T. Fuzzy probabilistic assessment of the impact of orrosion on fatigue of aircraft structures[J]. Journal of Sound and Vibration,2001(1):2003-1640.
[73]张延化,王优强,卞荣.灰色GM(1,1)模型在齿轮疲劳寿命预测中的应用[J]机械传动,2009(3)：100-101.
[74]冯刚,孙立德,黄洪钟等.疲劳寿命的模糊可靠度计算方法[J]中国机械工程,2003(19)：1699-1701.
[75]Carr M.J., Wang W., Modeling failure modes for residual life prediction using stochastic filtering theory[J]. Transactions on Reliability,2010,59(2):346-355.
[76]Wang Wenbin, Matthew. A Stochastic Filtering Based Data Driven Approach for Residual Life Prediction and Condition Based Maintenance Decision Making Support[C].2010 Prognostics & System Health Management Conference(PHM2010 Macau):2010:1-10.
[77]Peng Z,Chu F,HeY.Vibration signal analysis and feature extraction based on re-assigned wavelet scalogram[J]Joumal of Sound and Vibration,2002,253(5):1087-1100.
[78]McCormick A.C., Nandi A.K.Cyclic statistics in rolling bearing diagnosis[J]. Journal of Sound and Vibration,Volume 267,Issue 2,16 October 2003,Pages 253-265.
[79]Goerlich J.,Signal Analysis Using Spectral Correlation Measurement[C].IEEE Instrumentation and Measurement Technology Conferenece,1998:1313-1318.
[80]Li Li, Qu Liangsheng, Cyclic statistics in rolling bearing diagnosis[J]. Journal of Sound and Vibration, 2003(10):253-265.
[81]何俊,陈进,毕果等.谱相关函数的解调原理分析[J]机械科学与技术,2005(7)：771-774.
[82]何俊,陈进,毕果等.循环平稳度解调频原理分析及其在齿轮故障诊断中的应用[J]上海交通大学学报,2007(11)：1863-1866.
[83]R.B.Randall. The Relationship Between Spectrual Correlation and Envelope Analysis in the Diagnosis of Bearing Faluts and Other Cyclostationary Machine Signals[J]. Mechanical Systems and Signal Processing,2001(5):945-962.
[84]苏中元,贾民平,许飞云等.循环双谱及在周期平稳类故障中的应用[J].中国工程科学,2006(9)：57-60.
[85]金大玮.循环平稳理论及在齿轮箱故障诊断中的应用[D].江苏：东南大学,2006.
[86]姜鸣,陈进,秦恺等.循环周期图在滚动轴承故障诊断中的应用[J].机械科学与技术,2002(1)：108-110.
[87]Zhu Z.K., Feng Z.H., Kong E.R., Cyclostationarity analysis for gearbox condition monitoring: Approaches and effectiveness[J]Mechanical Systems and Signal Processing.2005,19(4):467-482.
[88]Frederic Bonnardot, R.BRandall, Francois Gruillet. Extraction of second-order cyclostationary source-Application to vibration analysis[J]Mechanical Systems and Signal Processing,2005(19):1230-1244.
[89]康海英,峦军英,张志斌等.基于时频和频谱分析的齿轮箱故障诊断[J].军械工程学院学报,2004.16(3)：10-13.
[90]姜鸣.循环统计量理论及其在滚动轴承故障诊断中的应用研究[D].上海：上海交通大学机械,2005.
[91]陈进,姜鸣.高阶循环统计量理论在机械故障诊断中的应用[J].振动工程学报,2001,14(02)：125-134.
[92]褚福磊,彭志科,冯志鹏等.机械故障诊断中的现代信号处理方法[M].2009：173-175.
[93]Ypma A,LeshemA,Duin RPW. Blind separation of rotating machine sources:bilinear forms and convolutive mixtures[J]. Neuro-computing,2002,49(4):349-368.
[94]Gelle G,Colas M,Delaunay G. Blind source separation applied to rotating machines monitoring by acoustical and vibrations analysis[J]. Mechanical System and Signal Processing,2000,14(3):427-442.
[95]胥永刚,李强,王正英等.基于独立分量分析的机械故障信息提取[J].天津大学学报,2006,39(9)：1066-1071.
[96]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(4)：481-483.
[97]Hyvarinen A, Oja E. Independent component analysis:algo-rithms and applications[J]. Neural Networks,2000,(13):411-430.
[98]Md. Shamim Reza, Mohammed Nasser, Md.Shahjaman. An Improved Version of Kurtosis Measure and Their Application in ICA[J]. International Journal of Wireless Communication and Information Systems2011(4):6-11.
[99]Shamim, M.Nasser. An improved version of kurtosis estimator and their application in ICA[C].13th International conference on computer and information Technology, Program book,2010:73-78.
[100]李舜酩,杨涛.基于峭度的转f振动信号盲识别[J].应用力学学报,2007(4)：560-565.
[101]毋文峰,陈小虎,苏勋家等.基于峭度的ICA特征提取和齿轮泵故障诊断[J].机械科学与技术,2011(9)：1853-1857.
[102]Zamanian, Amir Hosein, Ohadi, et al. Gear fault diagnosis based on Gaussian correlation of vibrations signals and wavelet coefficients[J]. Applied Soft Computing Journal,2011(12):4807-4819.
[103]Manuel Davya, Frederic Desobryb, Arthur Grettonc, et al, An online support vector machine for abnormal events detection[J]. Preprint submitted to Elsevier Science.2006(8):2009-2025.
[104]肖健华,吴今培,樊可清等.基于支持向量机的齿轮故障诊断方法[J].中国制造业信息化,2003(2)：107-109.
[105]于德介,杨宇,程军圣.-种基于SVM和EMD的齿轮故障诊断方法[J].机械工程学报,2005(1)：140-144.
[106]张超,陈建军,郭迅.基于EMD能量熵和支持向量机的齿轮故障诊断方法[J].振动与冲击,2010(10)：216-220,261.
[107]蒋玲莉,刘义伦,李学军等.基于SVM与多振动信息融合的齿轮故障诊断[J].中南大学学报(自然科学版),2010(12)：2184-2188.
[108]邱绵浩,王自营,安钢等.基于核主元分析与纠错输出编码SVM的齿轮故障诊断[J].振动与冲击,2009(5)：1-6.
[109]龚小平,崔利杰,仝崇楼.基于弹流润滑理论的斜齿圆柱齿轮油膜厚度影响参数分析[J].润滑与密封,2008(11)：73-76.
[110]丁康,李巍华,朱小勇.齿轮及齿轮箱故障诊断实用技术[M]北京：机械工业出版社,2005.
[111]陈静.基于有限元方法的重型车变速器整体动态模拟与寿命预测研究[D],吉林：吉林大学,2009.
[112]Vecer P, Kreidl M, Smid R. Condition indicators for gearbox condition monitoring systems[J], Czech Technical University in Prague.2005(6):35-43.
[113]赵富强.细高齿齿形优化设计及有限元强度分析[D].山西太原理工大学,2009.
[114]Troyer T.De, Guillaume P, Pintelon R., et al. Fast calculation of confidence intervals on parameter estimates of least-squares frequency-domain estimators[J]. Mechanical Systems and Signal Processing, 2009(2):261-273.
[115]Jan Helsen, Frederik Vanhollebeke, Ben Marrant, et al. Multibody modelling of varying complexity for modal behaviour analysis of wind turbine gearboxes[J]. Renewable Energy,2011(11):3098-3113.
[116]刘国光,李军杰,张德文.模态综合的多级子结构分析--两种改进装配法[J].航空学报,1982(4)：28-35.
[117]]恽伟君.多重动态子结构法在大型复杂结构动态计算中的应用[J].振动与冲击,1987(1)：1-11.
[118]赵勇铭.多轴疲劳寿命模型及疲劳试验谱编制方法研究[D],江苏：南京航空航天大学,2009.
[119]Leonard M.,Fundamentals of vibrations[M] NewYork:MCGraw-Hill,2001.
[120]石琴,陈朝阳,钱锋MIMO时域模态分析理论在车辆动态设计中的应用[J].农业机械学报,2003(7)：8-10.
[121]马俊,张建国,王泓等.温度对齿轮钢16Cr3NiWMoVNbE应变疲劳性能的影响[J].机械科学与技术,2011(6)：883-887.
[122]苏中元.旋转机械周期平稳类故障若干信号分析方法研究[D],江苏：东南大学,2008.
[123]王定成.支持向量机建模预测与控制[M].北京：气象出版社,2009.
[124]Burges C.J.C., Geometry and invariance in kernel based methods[M]Advance in Kernel Method support Veetor Learning.Cambridge:MITPress,1999.
[125]HuangH Z. Calculation of fuzzy reliability in the case of random stress and fuzzy fatigue strength[J]Chinese Journal of Mechanical Engineering,2000 (3):197-200,223.
[126]贾星兰,刘文珽.谱载下基于模糊Miner法则的疲劳寿命估算[J].北京航空航天大学学报,2003(3)：218-220.
[127]李青.核优化方法[D].西安：西安电子科技大学,2007.
[128]Zhao fuqiang,Wang tie,Li hongmei,et al. Fuzzy optimization design method on fine-pitch tooth profile[C]. Advanced Materials Research,2010(156-157):1029-1036.
[2]Wang Tie,Shen Jun,Zhao Fuqiang.Modular design on basic parameters of volume reducer[C].Applied Mechanics and Materials.2011,vol.86:633-636.
[3]刘义伦.工程构件疲劳寿命预测理论与方法[M].湖南科学技术出版社,1997：3-3.
[4]袁熙,李舜酩.疲劳寿命预测方法的研究现状与发展[J].航空制造技术,2005(12)：80-84.
[5]Galietti UMorabito, Annaeva E.Energy-analysis of fatigue damage by thermographic technique.Proceedings of SPIE-The International Society for Optical Engineering, Orlando, vol.4,2002:456-463.
[6]姚磊江,童小燕,吕胜利.关于疲劳劳能量理论若干问题的讨论[J].机械强度,2004(26)：278-281.
[7]Jiang M X, Yong C Z.Dynamic modeling of degradation data[C].IEEE Proceedings Annual Reliability and Maintain-ability Symposium,2002:607-610.
[8]Atzori B, Lazzarin P, Meneghetti G.Fracture mechanics and notch sensitivity[J]. Fatigue and Fractureof Engineering Material and Structures,2003,26(3):257-267.
[9]Verreman Y, Limodin N.Fatigue notch factor and short crack propagation[J]. Engineering Fracture Me-chanics,2008,75(6):1320-1335.
[10]Atzori B, Meneghetti G, Susmel L.Fatigue behav-iour AA356-T6 cast aluminium alloy weakened bycracks and notches[J]. Engineering Fracture Mechan-ics,2004,71(4-6):759-768.
[11]Repetto M P Cycle counting methods for bi-modal stationary Gaussian processes[J]. Probabilistic Engineering Mechanics,2005(20):229-238.
[12]M.Grigoriu.A spectral representation based modal for Monte Carlo simulation[J]. Probabilistic Engineering Mechanics,2000,15:365-370.
[13]Chapetti M D.Fatigue propagation threshold of short cracks under constant amplitude loading[J]. International Journal of Fatigue,2003,25(12):1319-1326.
[14]Forth S C, Newman J C, Forman R G.On generating fatigue crack growth thresholds[J]. International Journal of Fatigue,2003,25(1):9-15.
[15]Beretta S, Carboni M, Madia M.Modelling of fatigue thresholds for small cracks in a mild steel by"Strip-Yield"model[J]. Engineering Fracture Mechanics,2009,76(10):1548-1561.
[16]冯胜,程燕平,赵亚丽等.线性疲劳劳损伤累积理论的研究[J].哈尔滨工业大学学报,2003(5)：608-610.
[17]贡金鑫,王海超,赵国藩.结构疲劳累积损伤与极限承载能力可靠度[J].大连理工大学学报,2002(6)：714-717.
[18]姚磊江.疲劳过程中的能量耗散分析及基于能量耗散的疲劳损伤模型[D].陕西：西安西北工业大学,2004.
[19]侯善芹,许金泉.基于疲劳特征长度概念的-种新疲劳理论[J].上海交通大学学报,2010(10)：1443-1448.
[20]沈海军,郭万林,冯谦.材料S-N、ε-N及da/dN-ΔK疲劳性能数据之间的内在联系[J].机械强度2003(5)：556-560.
[21]叶笃毅,王德俊,童小燕等.一种基于材料韧性耗散分析的疲劳损伤定量新方法[J].实验力学,1999(1)：80-88.
[22]Orchard M E. A Particle Filtering-based Framework for On-line Fault Diagnosis and Failure Prognosis[D]. Georgia:Georgia Institute of Technology,2006.
[23]Marcos E,et al. A novel RSPF approach to prediction to prediction of high-risk,low-probability failure event[C] Annual Conference of the Prognostics and Health Management Society,2009.
[24]Chelidze D,et al. A dynamical systems approach to damage evolution tracking part 1 description and experimental application[J]Journal of Vibration and Acoustics,2002(124):250-257.
[25]滕红智,赵建民,贾希胜等.基于状态空间模型的齿轮磨损预测研究[J].机械科学与技术,2011(12)：2086-2091.
[26]王秋景,管迪华.汽车零部件加速疲劳试验方法[J].汽车技术,1997,11(1)：14-17.
[27]XIONG J J, SHENOI R A.A load history generation approach for full-scale accelerated fatigue tests[J]Engineering Fracture Mechanics,2008,75(12):3226-3243.
[28]RAJU P R, SATYANARAYANA B B, BABU K S.Evaluation of fatigue life of aluminum alloy wheels under radial loads[J]Engineering Failure Analysis 2007,14(4):791-800.
[29]PALIN-LUC T, BANVILLET A, VITTORI J P.How to reduce the duration of multiaxial fatigue tests under proportional service load[J]International Journal of Fatigue 2006,28(4):554-563.
[30]王秋景.工程疲劳寿命估算及对汽车前后轴疲劳试验方法的评价[D].北京：消华大学,1996.
[31]李国云,秦大同.风力发电机齿轮箱加速疲劳试验技术分析[J].重庆大学学报,2009(11)：1253-1255.
[32]卢曦,郑松林.轿车主减速器齿轮疲劳寿命的试验研究[J].机械强度,2008(4)：664-667.
[33]蒋荟.加速疲劳劳试验谱块的高载循环丢失问题及其解决方法[JJ.机械工程学报,2010(5)：194-197.
[34]张洪才,黄克正,陈举华等.秋基于断裂力学理论的表面淬火齿轮疲劳劳寿命的数值计算[J].应用力学学报,2004(3)：17-21.
[35]陈东升,钟其水,陈欣.车辆变速箱齿轮弯曲疲劳寿命的估算[J].机械设计,2002(5)：36-40.
[36]王小群,边新孝,邱丽芳等.40MnB调质齿轮弯曲疲劳强度的试验研究[J].机械传动,2003(2)：51-53.
[37]张君彩,边新孝,郑文林等35SIMn调质齿轮弯曲疲劳强度的试验研究[J].河北科技大学学报,2003(3)：63-66.
[38]武志斐,王铁,张瑞亮18Cr2Ni4WA齿轮接触疲劳特性试验研究[J].兵工学报,2010(5)：598-602.
[39]李红梅,王铁,张瑞亮.齿轮接触疲劳极限应力快速测定法的应用[J].机械传动,2010(5)：95-98.
[40]赵富强,于铁42CrMo钢渗碳淬火齿轮弯曲疲劳极限快速测定[J].机械设计与研究,2011(4)：77-79.
[41]Wang Tie, Li Hongmei, Zhang Ruiliang, et al Research on gear contact fatigue stress test[C].Applied Mechanics and Materials,2011(86):825-828.
[42]祁倩,王永,刘世军等42CrMo调质及表面淬火渐开线齿轮弯曲疲劳强度试验[J].机械传动,2010(9)：69-71.
[43]王国军,闫清东,项昌乐等18Cr2Ni4WA渗碳淬火齿轮弯曲疲劳特性试验研究[J].机械传动,2006(5)：46-59.
[44]尚德广,王德俊.多轴疲劳劳强度[M].北京：科学出版社,2007.
[45]Carpinteri A, Spagnoli A.Multiaxial high-cycle fatigue criterion for hard metals[J]. International Journal of Fatigue,2001(23):135-145.
[46]Spagnoli A. A new high-cycle fatigue criterion applied to out-of-phase biaxial stress state[J]. International Journal of Mechanical Sciences 2001(43):2581-2595.
[47]Wang YY, Yao WX.Evaluation and comparison of several multiaxial fatigue criteria[J].International Journal of Fatigue,2004,26(1):17-25
[48]Farahani AV. A new energy critical plane parameter for fatigue life assessment of various metallic materials subjected to in-phase and out-of-phase multiaxial fatigue loading conditions[J]. International Journal of Fatigue 2000(22):295-305.
[49]于海生,谢.尼.舒卡耶夫,王兴国等.一种多轴非比例载荷低周疲劳寿命预测方法[J].机械强度,2004(S1)：250-253.
[50]尚德广,王大谦,孙国芹等.多轴疲劳裂纹扩展行为研究[J].机械强度,2004,26(4)：423-427.
[51]Benedetti M., Fontanari V., Hohn B.R. Influence of shot peening on bending tooth fatigue limit of casehardened gears[J]. International Journal of Fatigue,2002(24):1127-1136.
[52]Glodez S., M.Sraml, J.Kramberger. A computational model for determination of service life of gears[J]International Journal of Fatigue,2002,24(10):1013-1020.
[53]J.Kramberger, M.raml, I.Potro.Numerical calculation of bending fatigue life of thin-rim spur gears[J]Engineering Fracture Mechanics,2004(71):647-656.
[54]E.Akata, M.T.Altmbalik, Y.Can.Three point load application in single tooth bending fatigue test for evaluation of gear blank manufacturing methods[J] International journal of Fatigue,2004,26(7):785-789.
[55]G. Fajdiga, M.Sraml. Fatigue crack initiation and propagation under cyclic contact loading[J]. Engineering Fracture Mechanics,2009(9):1320-1335.
[56]章文强,盛云等.燃料电池轿车变速器齿轮强度分析及疲劳寿命计算[J].传动技术,2009(3)：23-47.
[57]Akpan U O, Rushton P A and Koko S T.Development of a fuzzy probabilistic methodology for multiple-site fatigue damage[J]. Journal of aircraft,2004,41(3):633-640.
[58]张玉瑞,陈剑波.基于RBF神经网络的时间序列预测[J].计算机工程与应用用,2005(11)：74-76.
[59]张嵩,汪元美.基于广义径向基函数神经网络的非非线性时间序列预测器[J].电子科学学刊,2000(6)：965-971.
[60]王丽娜.渐开线齿轮传动疲劳寿命分析[D].山西：太原理工大学,2009.
[61]邓乃扬,田英杰.支持向量机-理论、算法与拓展[M].北京：科学出版社,2009.
[62]VapnikVN.Statistical Learning Theory[M]Newyork, Springer,1998.
[63]Suykens J.A.K.,Vandewalle J.,Moor D.B. OPtimal Control by Least squares Support Vector Maehines[J]. Neural Networks,2001.14(1):23-35.
[64]Platt J. Fast training of support vector machines using sequential minimal optimization [C].Scholkopf B, Burges C., Smola A.Advances in KernelMethods-Support Vector Learning.Cambridge:MIT Press, 1999:185-208.
[65]Platt J.using analytic QP and sparseness to speed training f support vectormachines [C].KearnsM, Solla S, CohnD. Advances in Neural Information Processing Systems. Cambridge:MIT Press,1999:557-563.
[66]Francis E.Htay, Cao L J. Application of support vector machines in financial time series forecasting[J]Omega,2001(29):309-317.
[67]朱家元,段宝君,张恒喜.新型SVM对时间序列预测研究[J].计算机科学,2003(8)：124-125.
[68]奉国,朱思铭.改进SVM及其在时间序列数据预测中的应用[J].华南理工大学学报,2005(5)：19-22.
[69]江田汉,束炯.基于LSSVM的混沌时间序列的多步预测[J].控制与决策,2006(1)：77-80.
[70]Suykens J A K,Gestel T V,Brahanter J D,et al. Least Squares Support Vector Machines[M].River Edge: World Scientific,2002:71-148.
[71]王旭亮.不确定性疲劳寿命预测方法研究[D].江苏：南京航空航天大学,2009.
[72]Akpan U O, Rushton P A and Koko S T. Fuzzy probabilistic assessment of the impact of orrosion on fatigue of aircraft structures[J]. Journal of Sound and Vibration,2001(1):2003-1640.
[73]张延化,王优强,卞荣.灰色GM(1,1)模型在齿轮疲劳寿命预测中的应用[J]机械传动,2009(3)：100-101.
[74]冯刚,孙立德,黄洪钟等.疲劳寿命的模糊可靠度计算方法[J]中国机械工程,2003(19)：1699-1701.
[75]Carr M.J., Wang W., Modeling failure modes for residual life prediction using stochastic filtering theory[J]. Transactions on Reliability,2010,59(2):346-355.
[76]Wang Wenbin, Matthew. A Stochastic Filtering Based Data Driven Approach for Residual Life Prediction and Condition Based Maintenance Decision Making Support[C].2010 Prognostics & System Health Management Conference(PHM2010 Macau):2010:1-10.
[77]Peng Z,Chu F,HeY.Vibration signal analysis and feature extraction based on re-assigned wavelet scalogram[J]Joumal of Sound and Vibration,2002,253(5):1087-1100.
[78]McCormick A.C., Nandi A.K.Cyclic statistics in rolling bearing diagnosis[J]. Journal of Sound and Vibration,Volume 267,Issue 2,16 October 2003,Pages 253-265.
[79]Goerlich J.,Signal Analysis Using Spectral Correlation Measurement[C].IEEE Instrumentation and Measurement Technology Conferenece,1998:1313-1318.
[80]Li Li, Qu Liangsheng, Cyclic statistics in rolling bearing diagnosis[J]. Journal of Sound and Vibration, 2003(10):253-265.
[81]何俊,陈进,毕果等.谱相关函数的解调原理分析[J]机械科学与技术,2005(7)：771-774.
[82]何俊,陈进,毕果等.循环平稳度解调频原理分析及其在齿轮故障诊断中的应用[J]上海交通大学学报,2007(11)：1863-1866.
[83]R.B.Randall. The Relationship Between Spectrual Correlation and Envelope Analysis in the Diagnosis of Bearing Faluts and Other Cyclostationary Machine Signals[J]. Mechanical Systems and Signal Processing,2001(5):945-962.
[84]苏中元,贾民平,许飞云等.循环双谱及在周期平稳类故障中的应用[J].中国工程科学,2006(9)：57-60.
[85]金大玮.循环平稳理论及在齿轮箱故障诊断中的应用[D].江苏：东南大学,2006.
[86]姜鸣,陈进,秦恺等.循环周期图在滚动轴承故障诊断中的应用[J].机械科学与技术,2002(1)：108-110.
[87]Zhu Z.K., Feng Z.H., Kong E.R., Cyclostationarity analysis for gearbox condition monitoring: Approaches and effectiveness[J]Mechanical Systems and Signal Processing.2005,19(4):467-482.
[88]Frederic Bonnardot, R.BRandall, Francois Gruillet. Extraction of second-order cyclostationary source-Application to vibration analysis[J]Mechanical Systems and Signal Processing,2005(19):1230-1244.
[89]康海英,峦军英,张志斌等.基于时频和频谱分析的齿轮箱故障诊断[J].军械工程学院学报,2004.16(3)：10-13.
[90]姜鸣.循环统计量理论及其在滚动轴承故障诊断中的应用研究[D].上海：上海交通大学机械,2005.
[91]陈进,姜鸣.高阶循环统计量理论在机械故障诊断中的应用[J].振动工程学报,2001,14(02)：125-134.
[92]褚福磊,彭志科,冯志鹏等.机械故障诊断中的现代信号处理方法[M].2009：173-175.
[93]Ypma A,LeshemA,Duin RPW. Blind separation of rotating machine sources:bilinear forms and convolutive mixtures[J]. Neuro-computing,2002,49(4):349-368.
[94]Gelle G,Colas M,Delaunay G. Blind source separation applied to rotating machines monitoring by acoustical and vibrations analysis[J]. Mechanical System and Signal Processing,2000,14(3):427-442.
[95]胥永刚,李强,王正英等.基于独立分量分析的机械故障信息提取[J].天津大学学报,2006,39(9)：1066-1071.
[96]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(4)：481-483.
[97]Hyvarinen A, Oja E. Independent component analysis:algo-rithms and applications[J]. Neural Networks,2000,(13):411-430.
[98]Md. Shamim Reza, Mohammed Nasser, Md.Shahjaman. An Improved Version of Kurtosis Measure and Their Application in ICA[J]. International Journal of Wireless Communication and Information Systems2011(4):6-11.
[99]Shamim, M.Nasser. An improved version of kurtosis estimator and their application in ICA[C].13th International conference on computer and information Technology, Program book,2010:73-78.
[100]李舜酩,杨涛.基于峭度的转f振动信号盲识别[J].应用力学学报,2007(4)：560-565.
[101]毋文峰,陈小虎,苏勋家等.基于峭度的ICA特征提取和齿轮泵故障诊断[J].机械科学与技术,2011(9)：1853-1857.
[102]Zamanian, Amir Hosein, Ohadi, et al. Gear fault diagnosis based on Gaussian correlation of vibrations signals and wavelet coefficients[J]. Applied Soft Computing Journal,2011(12):4807-4819.
[103]Manuel Davya, Frederic Desobryb, Arthur Grettonc, et al, An online support vector machine for abnormal events detection[J]. Preprint submitted to Elsevier Science.2006(8):2009-2025.
[104]肖健华,吴今培,樊可清等.基于支持向量机的齿轮故障诊断方法[J].中国制造业信息化,2003(2)：107-109.
[105]于德介,杨宇,程军圣.-种基于SVM和EMD的齿轮故障诊断方法[J].机械工程学报,2005(1)：140-144.
[106]张超,陈建军,郭迅.基于EMD能量熵和支持向量机的齿轮故障诊断方法[J].振动与冲击,2010(10)：216-220,261.
[107]蒋玲莉,刘义伦,李学军等.基于SVM与多振动信息融合的齿轮故障诊断[J].中南大学学报(自然科学版),2010(12)：2184-2188.
[108]邱绵浩,王自营,安钢等.基于核主元分析与纠错输出编码SVM的齿轮故障诊断[J].振动与冲击,2009(5)：1-6.
[109]龚小平,崔利杰,仝崇楼.基于弹流润滑理论的斜齿圆柱齿轮油膜厚度影响参数分析[J].润滑与密封,2008(11)：73-76.
[110]丁康,李巍华,朱小勇.齿轮及齿轮箱故障诊断实用技术[M]北京：机械工业出版社,2005.
[111]陈静.基于有限元方法的重型车变速器整体动态模拟与寿命预测研究[D],吉林：吉林大学,2009.
[112]Vecer P, Kreidl M, Smid R. Condition indicators for gearbox condition monitoring systems[J], Czech Technical University in Prague.2005(6):35-43.
[113]赵富强.细高齿齿形优化设计及有限元强度分析[D].山西太原理工大学,2009.
[114]Troyer T.De, Guillaume P, Pintelon R., et al. Fast calculation of confidence intervals on parameter estimates of least-squares frequency-domain estimators[J]. Mechanical Systems and Signal Processing, 2009(2):261-273.
[115]Jan Helsen, Frederik Vanhollebeke, Ben Marrant, et al. Multibody modelling of varying complexity for modal behaviour analysis of wind turbine gearboxes[J]. Renewable Energy,2011(11):3098-3113.
[116]刘国光,李军杰,张德文.模态综合的多级子结构分析--两种改进装配法[J].航空学报,1982(4)：28-35.
[117]]恽伟君.多重动态子结构法在大型复杂结构动态计算中的应用[J].振动与冲击,1987(1)：1-11.
[118]赵勇铭.多轴疲劳寿命模型及疲劳试验谱编制方法研究[D],江苏：南京航空航天大学,2009.
[119]Leonard M.,Fundamentals of vibrations[M] NewYork:MCGraw-Hill,2001.
[120]石琴,陈朝阳,钱锋MIMO时域模态分析理论在车辆动态设计中的应用[J].农业机械学报,2003(7)：8-10.
[121]马俊,张建国,王泓等.温度对齿轮钢16Cr3NiWMoVNbE应变疲劳性能的影响[J].机械科学与技术,2011(6)：883-887.
[122]苏中元.旋转机械周期平稳类故障若干信号分析方法研究[D],江苏：东南大学,2008.
[123]王定成.支持向量机建模预测与控制[M].北京：气象出版社,2009.
[124]Burges C.J.C., Geometry and invariance in kernel based methods[M]Advance in Kernel Method support Veetor Learning.Cambridge:MITPress,1999.
[125]HuangH Z. Calculation of fuzzy reliability in the case of random stress and fuzzy fatigue strength[J]Chinese Journal of Mechanical Engineering,2000 (3):197-200,223.
[126]贾星兰,刘文珽.谱载下基于模糊Miner法则的疲劳寿命估算[J].北京航空航天大学学报,2003(3)：218-220.
[127]李青.核优化方法[D].西安：西安电子科技大学,2007.
[128]Zhao fuqiang,Wang tie,Li hongmei,et al. Fuzzy optimization design method on fine-pitch tooth profile[C]. Advanced Materials Research,2010(156-157):1029-1036.