基于统计学习理论的故障分析与可靠度预测技术研究
|
摘要
如何有效地识别和分析产品故障,并在此基础上进行产品可靠度预测,对于企业预防产品故障和制定产品维修计划,具有十分重要的意义。随着产品的可靠性不断提高,能够获得的产品的故障数据变得十分有限,因而难以通过大量故障数据的分析进行故障识别。在此背景下,本文研究了基于统计学习理论的产品故障分析及可靠度预测技术,并开发了原型系统进行验证。
在研究故障分析与可靠度预测系统工作原理的基础上,建立了该系统的体系结构。
针对机械产品的故障大多属于小子样问题,利用统计学习理论和支持向量机进行故障模式识别,并将支持向量机的二分类方法和多分类方法分别用于汽车发动机单一故障识别和多故障识别之中。该方法较为有效的避免以往机器学习方法在小子样条件下表现不佳的情形。
在利用支持向量机有效的识别产品故障模式之后,将FMEA和FTA相结合起来进行故障分析,该方法不但能够弥补FMEA或FTA分析技术各自的不足,而且能够实现从FMEA表格到FTA故障树的自动生成,更加有效的找出具体故障原因。
研究了基于统计学习理论的产品性能退化趋势的线性回归方法,实现了利用退化数据进行退化方式相关条件下的产品可靠度预测,并以发动机机壳为对象进行了实例研究。结果表明,该方法能比较准确地判断退化型故障产品的可靠度是否低于用户允许的限度。
开发了故障分析和可靠度预测原型系统,对上述理论和技术进行了验证。
Reliability prediction based on effective identification and analysis of failure is very meaningful to the enterprises in failure prevention and maintains scheduling. With the improvement of product reliability, it is difficult to acquire enough data used to identify failure based on data analysis. Technologies of failure analysis and reliability prediction based on statistical learning theory are presented. A prototype system is developed for validation.
The framework structure of failure analysis and reliability prediction system is built based on the analysis of work principle.
The statistical learning theory and support vector machines are introduced to identify the mechanical product failure, which is a typical small-sample problem. The binary classification method and the multi-classification method are applied in the classification of single failure and multi-failure mode in automobile engine. The result shows that the statistical learning theory and support vector machines can improve the accuracy compared to the conventional machine learning methods.
The FTA and FMEA are integrated to analyze the failure modes identified by the support vector machines. The new method can lessen the limitation of FMEA or FTA. Meanwhile, the Fault Tree (FT) can be generated automatically by the FMEA tabulation, which is help to effectively identify the specific cause of failure.
The linear regression method of degradation prediction based on the statistical learning theory is presented. The degradation data is used to predict the reliability of product with related degradation modes. A case study is given taking the shell of the automobile engine as an example. The result shows that this method can accurately judge whether the reliability of the product is lower than the customer’s expectation.
A failure analysis and reliability prediction system is developed to validate the theory and methods mentioned above.
在研究故障分析与可靠度预测系统工作原理的基础上,建立了该系统的体系结构。
针对机械产品的故障大多属于小子样问题,利用统计学习理论和支持向量机进行故障模式识别,并将支持向量机的二分类方法和多分类方法分别用于汽车发动机单一故障识别和多故障识别之中。该方法较为有效的避免以往机器学习方法在小子样条件下表现不佳的情形。
在利用支持向量机有效的识别产品故障模式之后,将FMEA和FTA相结合起来进行故障分析,该方法不但能够弥补FMEA或FTA分析技术各自的不足,而且能够实现从FMEA表格到FTA故障树的自动生成,更加有效的找出具体故障原因。
研究了基于统计学习理论的产品性能退化趋势的线性回归方法,实现了利用退化数据进行退化方式相关条件下的产品可靠度预测,并以发动机机壳为对象进行了实例研究。结果表明,该方法能比较准确地判断退化型故障产品的可靠度是否低于用户允许的限度。
开发了故障分析和可靠度预测原型系统,对上述理论和技术进行了验证。
Reliability prediction based on effective identification and analysis of failure is very meaningful to the enterprises in failure prevention and maintains scheduling. With the improvement of product reliability, it is difficult to acquire enough data used to identify failure based on data analysis. Technologies of failure analysis and reliability prediction based on statistical learning theory are presented. A prototype system is developed for validation.
The framework structure of failure analysis and reliability prediction system is built based on the analysis of work principle.
The statistical learning theory and support vector machines are introduced to identify the mechanical product failure, which is a typical small-sample problem. The binary classification method and the multi-classification method are applied in the classification of single failure and multi-failure mode in automobile engine. The result shows that the statistical learning theory and support vector machines can improve the accuracy compared to the conventional machine learning methods.
The FTA and FMEA are integrated to analyze the failure modes identified by the support vector machines. The new method can lessen the limitation of FMEA or FTA. Meanwhile, the Fault Tree (FT) can be generated automatically by the FMEA tabulation, which is help to effectively identify the specific cause of failure.
The linear regression method of degradation prediction based on the statistical learning theory is presented. The degradation data is used to predict the reliability of product with related degradation modes. A case study is given taking the shell of the automobile engine as an example. The result shows that this method can accurately judge whether the reliability of the product is lower than the customer’s expectation.
A failure analysis and reliability prediction system is developed to validate the theory and methods mentioned above.
引文
[1]张春华,温熙森.加速寿命试验技术综述.兵工学报,2004,25(4):485-491
[2]严拴航,师义民.恒应力加速寿命试验中无失效数据的处理.纯粹数学与应用数学,2006,22(3):145-148
[3]赵建印,孙权.基于加速退化试验数据的可靠性分析.可靠性分析与研究,2005,7(1):123-127
[4] Crk V. Reliability assessment from degradation data. Proc. Annual Reliability and Maintainability Symposium,2000
[5]盐见弘,岛冈淳.故障模式和影响分析与故障树分析的应用.机械工业出版社,1997:123-125
[6]钱耀义.基于人工神经网络技术的发动机故障诊断系统,吉林工业大学研究生学位论文,2004
[7]王伟杰,康元福.基于小波神经网络的汽车发动机故障诊断研究,哈尔滨工业大学研究生学位论文,2003
[8]祝海龙.统计学习理论的工程应用,西安交通大学博士学位论文,2002
[9]朱永生.支持向量机及其在机械故障模式识别中的应用,西安交通大学博士学位论文,2003
[10]边肇祺,张学工.模式识别(第二版).北京:清华大学出版社. 2000
[11] Vapnik V. Statistical Learning theory. New York: John Wiley & Sons, 1998
[12] Scholkopf B, Smola A J. Learning with kernels. Cambridge, MA MIT Press, 2002
[13] Scholkopf B, Plat J C, Shawe-Taylor J, et al. Estimating the support of a high- dimensional distribution. Neural Computation, 2001, 13(7): 1443-1471
[14]陈毅松,汪国平,董士海.基于支持向量机的渐进直推式分类学习方法.软件学报,2003,14(3):451-460
[15]李蓉,叶世伟,史忠植.SVM KNN分类器——一种提高SVM分类精度的新方法.电子学报,30(5):745-748
[16] Yiqiang Zhang, Dinggang Shen. Design efficient support vector machine for fast classification. Pattern Recognition, 2005,38:157-161
[17] Zhang X. Using class-center vectors to build support vector machines. In proceedings of NNSP’99, 1999
[18] Mao K Z. Feature subset selection for support vector machines through discriminative function pruning analysis. IEEE Transaction on Systems, Man, and Cybernetics Part B: Cybernetics, 2004, 34(1): 60-67
[19]张学工译.统计学习理论的本质.北京:清华大学出版社,2000
[20] Osuna E, Freund R, Girosi F. An improved training algorithm for support vector machines. Proceedings of the 1997 IEEE Workshop on Nerual Networks for signal Processing. IEEE, 1997, 276-285
[21] Platt J. Fast training of support vector machines using sequential minimal optimization. Advance in kernel methods s-Support Vector Learning. Cambridge: MIT Press, 1999:185-208
[22] Ayat NE, Cheriet M, Remakil, et al. KMOD a new support vector machine kernel with moderate decreasing for Pattern recognition, application to digitimage recognition. Proceedings of 6th International Conference on Document Analysis and Recognition. Seattle, USA: IEEE, 2001, 1211-1215
[23] Arnaris-I, WU S. An information-geometrical method for improving the Performance of support vector machine chalssifiers. Proceedings of Artificial neral networks. 1999: 85-90
[24] Carlos Soares, Pavel B. Brazdil, Petr Kuba. A Meta Learning Method to Select the Kernel Width in Support Vector Regression. Machine Learning, 2004, 54: 195-209
[25] Lau K W, WU Q H. Leave one support vector out cross validation for fast estimation of generalization errors. Pattern Recognition, 2004, 37: 1835-1840
[26] Christopher J. Prece, Neil S. Taylor. FMEA for Multiple Failures, Reliability and Maintainability, 1998, 43-48
[27] Joseph A. Childs. A Modified FMEA Tool for Use in Identifying and Addressing Common Cause Failure Risks in Industry, Reliability and Maintainability Symposium, 1999, 19-25
[28] Zigmund Bluvband, Pavel Grabov. Expanded FMEA, Reliability and Maintainability Symposium, 2004, 31-37
[29] J. B. Dugan, S. J. Bavuso, M. A. Boyd. Dynamic Fault Tree Model for Fault-Tolerant Computer System, IEEE Trans On Reliability, 1992, 41(3): 363-377
[30] J. B. Dugan, K. J. Sullivan, D. Coppit. Developing a Low-Cost High-Quality Software Tool for Dynamic Fault-Tree Analysis, IEEE Trans On Reliability, 2000, 49(1): 49-59
[31] YAOYi-ping, YANGXiao-jun, LIPei-qiong. Dynamic Fault Tree Analysis for Fault- Tolerant Computer System, AIAA/IEEE Proceedings of 15th DASC(Digital Avionics Systems Conference), Atlanta: AIAA/IEEE, 1996, 479-484
[32]王阳阳,张代胜,孙海涛.FMEA和FTA综合分析法在汽车故障诊断和维修中的应用.汽车科技,2004,9(5):47-48
[33]张建国,黄文敏.大型机械产品FMEA和FTA综合分析方法.机械设计与制造,2000,2:1-4
[34]甘传付,曹宏炳等.基于FMECA和FTA的故障诊断和故障预报.系统工程与电子技术,2002,24(1):127-131
[35]陶建峰,王少萍等.计算机辅助FMEA与FTA正向综合分析方法研究.北京航空航天大学学报,2000,26(1):663-666
[36]赵廷弟.基于FMEA和FTA的智能故障诊断技术研究.北京:北京航空航天大学,2003
[37]董聪,郦正能,何庆芝.系统可靠性预测方法.强度与环境,1996(1):47-54
[38]陈家鼎,孙万龙,李补喜.关于无失效数据情形下的置信限.应用数学学报,18(1):90-100
[39]傅惠民,王凭慧.无失效数据的可靠性评估和寿命预测.机械强度,26(3):260-264
[40]茆诗松,夏剑锋,管文琪.轴承寿命试验中无失效数据的处理.应用概率统计,1993,9(3):326-331
[41]韩明.双参数指数分布无失效数据的Bayes估计.数学研究与评论,1999,19(1):141-145
[42]倪中新,费鹤良.威布尔分布无失效数据的统计分析.应用数学学报,2003,26(3):533-543
[43]王玲玲,王炳兴.无失效数据的统计分析—修正似然函数方法.数理统计与应用概率,1996,11(1):64-70
[44]韩明.基于无失效数据的加权Bayes估计.中国统计学报(台湾),2003,41(2):159-174
[45]韩明.多层先验分布的构造及其应用.运筹与管理,1997,6(3):31-40
[46]冯静,刘琦,周经纶等.基于性能退化数据的液体火箭发动机可靠性Bayes评定.航空计算技术,2003,33(3):6-11
[47]张永强,刘琦,周经纶.基于Bayes性能退化模型的可靠性评定.可靠性与环境适应性理论研究,2006,24(4):46-50
[48] Poyhonen S, Negrea M, Arkkio A, etc. Support vector classification for fault diagnosticsof an electrical machine. Proc. Of International conference on signal processing (ICSP’02),Beijing, China, August 26-30, 2002
[49] Junfeng Gao, Wengang Shi, Jianxun Tan, etc. Support vector machines based on approach for fault diagnosis of valves in reciprocating pumps. Proc. of the 2002 IEEE Canadian conference of electrical & computer engineering, 1622-1627
[50]肖健华,樊可清,吴今培等.应用于故障诊断的SVM理论研究.振动、测试与诊断. 2001,21(4):258-262
[51]肖健华,吴今培.样本数目不对称时的SVM模型.计算机科学,2003,30(2):165-167
[52]肖健华,樊可清,吴今培等.基于支持向量机的齿轮故障诊断方法.中国制造业信息化,2003,32(2):107-109
[53]马笑潇,黄席樾等.基于SVM二叉树分类算法及其在故障诊断中的应用.控制与决策,2002,18:272-276
[54]马笑潇,黄席樾,柴毅.基于支持向量机的故障过程趋势预测研究.系统仿真学报,2002,14(11):1548-1551
[55]马笑潇.智能故障诊断中的机器学习新理论及其应用,西安交通大学博士学位,2002
[56]张周锁,李凌均等.基于支持向量机的机械故障诊断方法研究.西安交通大学学报,2002,36(12):1303-1306
[57]董明,孟源源,徐长响等.基于支持向量机及油中溶解气体分析的大型电力变压器故障诊断模型研究.中国电机工程学报,2003,23(7):88-92
[58]杨云,朱家元,张恒喜.基于新型机器学习的电子装备系统智能故障诊断研究.计算机工程与应用,2003,22:210-213
[59]朱凌云,曹长修.基于支持向量机的缺陷识别方法.重庆大学学报(自然科学版),2002,25(6):42-45
[60]胡寿松.基于支持向量机的非线性系统故障诊断.控制与决策,2001,16(5):617-620
[61]徐启华,师军.基于支持向量机的航空发动机故障诊断.航空动力学报,2005,20(2):298-303
[62]王硕,唐建明,徐荣华.使用PCA及SVM算法进行滚动轴承故障检测.机电工程技术,2005,34(2):31-33
[63]朱志宇,张冰,刘维亭.模糊支持向量机在船舶柴油机故障诊断中的应用.中国造船,2006,47(3):64-70
[64]于德介,程军圣,杨宇等.一种基于经验模式分解与支持向量机的转子故障诊断方法.中国电机工程学报,2006,26(16):162-168
[65]毛志阳,陆爽.基于K-L变换和支持向量机的滚动轴承故障诊断.煤矿机械,2006,27(6):1084-1087
[66]陆有忠,杨有贞,张会林.边坡工程可靠性的支持向量机估计.岩石力学与工程学报,2005,24(1):149-154
[67]孟科,张恒喜,李寿安等.基于SVM的可靠性评估方法研究.中国制造业信息化,2004,10(9):109-110
[68]朱家元,杨云,张恒喜等.基于优化最小二乘支持向量机的小样本预测研究.航空学报,2004,25(6):555-559
[69]李洪双,吕震宙,岳珠峰.结构可靠性分析的支持向量机方法.应用数学和力学,2006,27(10):1135-1144
[70]李嘉.基于支持向量机的软件可靠性早期预测研究.合肥:合肥工业大学,2005
[71]杨叔子,史铁林.设备诊断技术的现状与未来.1995年全国设备诊断技术学术会议论文集,武汉:1995.3-8
[72] Hsu Chih-Wei, Lin Chih-Jen. A Comparison of Methods for Multiclass Support Vector Machines. IEEE Trans On Neural Networks, 2002, 13(2): 415-425
[73] J. Platt,N. Cristianini,J. Shawe-Taylor. Large margin DAGs for multiclass classification. S A Solla, T K Leen, K-R Muller. Advances in Neural Information Processing Systems. Massachusetts: MIT Press, 2000, 547-553
[74] Peng Wang, David W. Coit. Reliability based on Degradation Modeling for Systems with Multiple Degradation Measures. Reliability and Maintainability Symposium, 2004, 302-308
[75] Di Xu, Wenbiao Zhao. Reliability Prediction using Multivariate Degradation Data. Reliability and Maintainability Symposium, 2005, 337-342
[2]严拴航,师义民.恒应力加速寿命试验中无失效数据的处理.纯粹数学与应用数学,2006,22(3):145-148
[3]赵建印,孙权.基于加速退化试验数据的可靠性分析.可靠性分析与研究,2005,7(1):123-127
[4] Crk V. Reliability assessment from degradation data. Proc. Annual Reliability and Maintainability Symposium,2000
[5]盐见弘,岛冈淳.故障模式和影响分析与故障树分析的应用.机械工业出版社,1997:123-125
[6]钱耀义.基于人工神经网络技术的发动机故障诊断系统,吉林工业大学研究生学位论文,2004
[7]王伟杰,康元福.基于小波神经网络的汽车发动机故障诊断研究,哈尔滨工业大学研究生学位论文,2003
[8]祝海龙.统计学习理论的工程应用,西安交通大学博士学位论文,2002
[9]朱永生.支持向量机及其在机械故障模式识别中的应用,西安交通大学博士学位论文,2003
[10]边肇祺,张学工.模式识别(第二版).北京:清华大学出版社. 2000
[11] Vapnik V. Statistical Learning theory. New York: John Wiley & Sons, 1998
[12] Scholkopf B, Smola A J. Learning with kernels. Cambridge, MA MIT Press, 2002
[13] Scholkopf B, Plat J C, Shawe-Taylor J, et al. Estimating the support of a high- dimensional distribution. Neural Computation, 2001, 13(7): 1443-1471
[14]陈毅松,汪国平,董士海.基于支持向量机的渐进直推式分类学习方法.软件学报,2003,14(3):451-460
[15]李蓉,叶世伟,史忠植.SVM KNN分类器——一种提高SVM分类精度的新方法.电子学报,30(5):745-748
[16] Yiqiang Zhang, Dinggang Shen. Design efficient support vector machine for fast classification. Pattern Recognition, 2005,38:157-161
[17] Zhang X. Using class-center vectors to build support vector machines. In proceedings of NNSP’99, 1999
[18] Mao K Z. Feature subset selection for support vector machines through discriminative function pruning analysis. IEEE Transaction on Systems, Man, and Cybernetics Part B: Cybernetics, 2004, 34(1): 60-67
[19]张学工译.统计学习理论的本质.北京:清华大学出版社,2000
[20] Osuna E, Freund R, Girosi F. An improved training algorithm for support vector machines. Proceedings of the 1997 IEEE Workshop on Nerual Networks for signal Processing. IEEE, 1997, 276-285
[21] Platt J. Fast training of support vector machines using sequential minimal optimization. Advance in kernel methods s-Support Vector Learning. Cambridge: MIT Press, 1999:185-208
[22] Ayat NE, Cheriet M, Remakil, et al. KMOD a new support vector machine kernel with moderate decreasing for Pattern recognition, application to digitimage recognition. Proceedings of 6th International Conference on Document Analysis and Recognition. Seattle, USA: IEEE, 2001, 1211-1215
[23] Arnaris-I, WU S. An information-geometrical method for improving the Performance of support vector machine chalssifiers. Proceedings of Artificial neral networks. 1999: 85-90
[24] Carlos Soares, Pavel B. Brazdil, Petr Kuba. A Meta Learning Method to Select the Kernel Width in Support Vector Regression. Machine Learning, 2004, 54: 195-209
[25] Lau K W, WU Q H. Leave one support vector out cross validation for fast estimation of generalization errors. Pattern Recognition, 2004, 37: 1835-1840
[26] Christopher J. Prece, Neil S. Taylor. FMEA for Multiple Failures, Reliability and Maintainability, 1998, 43-48
[27] Joseph A. Childs. A Modified FMEA Tool for Use in Identifying and Addressing Common Cause Failure Risks in Industry, Reliability and Maintainability Symposium, 1999, 19-25
[28] Zigmund Bluvband, Pavel Grabov. Expanded FMEA, Reliability and Maintainability Symposium, 2004, 31-37
[29] J. B. Dugan, S. J. Bavuso, M. A. Boyd. Dynamic Fault Tree Model for Fault-Tolerant Computer System, IEEE Trans On Reliability, 1992, 41(3): 363-377
[30] J. B. Dugan, K. J. Sullivan, D. Coppit. Developing a Low-Cost High-Quality Software Tool for Dynamic Fault-Tree Analysis, IEEE Trans On Reliability, 2000, 49(1): 49-59
[31] YAOYi-ping, YANGXiao-jun, LIPei-qiong. Dynamic Fault Tree Analysis for Fault- Tolerant Computer System, AIAA/IEEE Proceedings of 15th DASC(Digital Avionics Systems Conference), Atlanta: AIAA/IEEE, 1996, 479-484
[32]王阳阳,张代胜,孙海涛.FMEA和FTA综合分析法在汽车故障诊断和维修中的应用.汽车科技,2004,9(5):47-48
[33]张建国,黄文敏.大型机械产品FMEA和FTA综合分析方法.机械设计与制造,2000,2:1-4
[34]甘传付,曹宏炳等.基于FMECA和FTA的故障诊断和故障预报.系统工程与电子技术,2002,24(1):127-131
[35]陶建峰,王少萍等.计算机辅助FMEA与FTA正向综合分析方法研究.北京航空航天大学学报,2000,26(1):663-666
[36]赵廷弟.基于FMEA和FTA的智能故障诊断技术研究.北京:北京航空航天大学,2003
[37]董聪,郦正能,何庆芝.系统可靠性预测方法.强度与环境,1996(1):47-54
[38]陈家鼎,孙万龙,李补喜.关于无失效数据情形下的置信限.应用数学学报,18(1):90-100
[39]傅惠民,王凭慧.无失效数据的可靠性评估和寿命预测.机械强度,26(3):260-264
[40]茆诗松,夏剑锋,管文琪.轴承寿命试验中无失效数据的处理.应用概率统计,1993,9(3):326-331
[41]韩明.双参数指数分布无失效数据的Bayes估计.数学研究与评论,1999,19(1):141-145
[42]倪中新,费鹤良.威布尔分布无失效数据的统计分析.应用数学学报,2003,26(3):533-543
[43]王玲玲,王炳兴.无失效数据的统计分析—修正似然函数方法.数理统计与应用概率,1996,11(1):64-70
[44]韩明.基于无失效数据的加权Bayes估计.中国统计学报(台湾),2003,41(2):159-174
[45]韩明.多层先验分布的构造及其应用.运筹与管理,1997,6(3):31-40
[46]冯静,刘琦,周经纶等.基于性能退化数据的液体火箭发动机可靠性Bayes评定.航空计算技术,2003,33(3):6-11
[47]张永强,刘琦,周经纶.基于Bayes性能退化模型的可靠性评定.可靠性与环境适应性理论研究,2006,24(4):46-50
[48] Poyhonen S, Negrea M, Arkkio A, etc. Support vector classification for fault diagnosticsof an electrical machine. Proc. Of International conference on signal processing (ICSP’02),Beijing, China, August 26-30, 2002
[49] Junfeng Gao, Wengang Shi, Jianxun Tan, etc. Support vector machines based on approach for fault diagnosis of valves in reciprocating pumps. Proc. of the 2002 IEEE Canadian conference of electrical & computer engineering, 1622-1627
[50]肖健华,樊可清,吴今培等.应用于故障诊断的SVM理论研究.振动、测试与诊断. 2001,21(4):258-262
[51]肖健华,吴今培.样本数目不对称时的SVM模型.计算机科学,2003,30(2):165-167
[52]肖健华,樊可清,吴今培等.基于支持向量机的齿轮故障诊断方法.中国制造业信息化,2003,32(2):107-109
[53]马笑潇,黄席樾等.基于SVM二叉树分类算法及其在故障诊断中的应用.控制与决策,2002,18:272-276
[54]马笑潇,黄席樾,柴毅.基于支持向量机的故障过程趋势预测研究.系统仿真学报,2002,14(11):1548-1551
[55]马笑潇.智能故障诊断中的机器学习新理论及其应用,西安交通大学博士学位,2002
[56]张周锁,李凌均等.基于支持向量机的机械故障诊断方法研究.西安交通大学学报,2002,36(12):1303-1306
[57]董明,孟源源,徐长响等.基于支持向量机及油中溶解气体分析的大型电力变压器故障诊断模型研究.中国电机工程学报,2003,23(7):88-92
[58]杨云,朱家元,张恒喜.基于新型机器学习的电子装备系统智能故障诊断研究.计算机工程与应用,2003,22:210-213
[59]朱凌云,曹长修.基于支持向量机的缺陷识别方法.重庆大学学报(自然科学版),2002,25(6):42-45
[60]胡寿松.基于支持向量机的非线性系统故障诊断.控制与决策,2001,16(5):617-620
[61]徐启华,师军.基于支持向量机的航空发动机故障诊断.航空动力学报,2005,20(2):298-303
[62]王硕,唐建明,徐荣华.使用PCA及SVM算法进行滚动轴承故障检测.机电工程技术,2005,34(2):31-33
[63]朱志宇,张冰,刘维亭.模糊支持向量机在船舶柴油机故障诊断中的应用.中国造船,2006,47(3):64-70
[64]于德介,程军圣,杨宇等.一种基于经验模式分解与支持向量机的转子故障诊断方法.中国电机工程学报,2006,26(16):162-168
[65]毛志阳,陆爽.基于K-L变换和支持向量机的滚动轴承故障诊断.煤矿机械,2006,27(6):1084-1087
[66]陆有忠,杨有贞,张会林.边坡工程可靠性的支持向量机估计.岩石力学与工程学报,2005,24(1):149-154
[67]孟科,张恒喜,李寿安等.基于SVM的可靠性评估方法研究.中国制造业信息化,2004,10(9):109-110
[68]朱家元,杨云,张恒喜等.基于优化最小二乘支持向量机的小样本预测研究.航空学报,2004,25(6):555-559
[69]李洪双,吕震宙,岳珠峰.结构可靠性分析的支持向量机方法.应用数学和力学,2006,27(10):1135-1144
[70]李嘉.基于支持向量机的软件可靠性早期预测研究.合肥:合肥工业大学,2005
[71]杨叔子,史铁林.设备诊断技术的现状与未来.1995年全国设备诊断技术学术会议论文集,武汉:1995.3-8
[72] Hsu Chih-Wei, Lin Chih-Jen. A Comparison of Methods for Multiclass Support Vector Machines. IEEE Trans On Neural Networks, 2002, 13(2): 415-425
[73] J. Platt,N. Cristianini,J. Shawe-Taylor. Large margin DAGs for multiclass classification. S A Solla, T K Leen, K-R Muller. Advances in Neural Information Processing Systems. Massachusetts: MIT Press, 2000, 547-553
[74] Peng Wang, David W. Coit. Reliability based on Degradation Modeling for Systems with Multiple Degradation Measures. Reliability and Maintainability Symposium, 2004, 302-308
[75] Di Xu, Wenbiao Zhao. Reliability Prediction using Multivariate Degradation Data. Reliability and Maintainability Symposium, 2005, 337-342