滚动轴承故障诊断的案例推理方法
付新哲张优云
朱永生
西安交通大学机械工程学院,710049,西安
摘要:针对滚动轴承的故障诊断问题,提出了一种采用案例推理(CBR)的诊断方法.为了解决检索
相似案例时案例属性多、人工确定关键属性及其权重困难的问题,提出了一种Filter/Wrapper复合型特征选择算法,用邻域粗糙集算法粗选属性,用遗传算法进一步精选属性和优化权重,并有效地解决了邻域粗糙集算法中需要人工确定邻域大小的问题.以滚动轴承运行时的振动信号为基本信息,建立了滚动轴承案例库,从案例库中检索与问题案例相似的历史案例,并根据这些历史案例来判定问题案例的故障类别.试验结果表明,故障诊断的正确率达到100%,故障位置诊断的正确卒达到93.3%,且算法具有较好的稳定性.
案例推理;滚动轴承;故障诊断
TH17A
0253-987X(2011) 11-0079-06
Rolling Bearing Fault Diagnosis Approach
Based on Case-Based Reasoning
FU Xinzhe ZHANG Youyun ZHU Yongsheng
2011-03-30
f寸新哲(1985-),男,硕士生;张优云(联系人),女,教授.
国家自然科学基
金资助项目(51035007).
]都被用
类型为
l和较高
结论
2010(10) : 130-131.
@@[6] WATSON I. Case-based reasoning is a methodology not a technology [ J ]. Knowledge-Based Systems,
1999, 12 (1/6): 303-308.
@@[7] GUYON I, ELISSEEFF A. An introduction to varia
ble and feature selection [J]. The Journal of Machine
Learning Research, 2003(3): 1157-1182.@@[8] UNCU O, TURKSEN I. A novel feature selection ap
proach: combining feature wrappers and filters [J].
Information Sciences, 2007, 177 (2): 449-466.@@[9] ZHU Z, ONG Y S, DASH M. Wrapper/filter feature selection algorithm using a memetic framework[J].
@@[1]王晓冬,何正嘉,訾艳阳.滚动轴承故障诊断的多小 波谱峭度方法[J].西安交通大学学报,2010,44 (3), 77-81.
WANG Xiaodong, HE Zhengjia, ZI Yanyang. Spectral
kurtosis of multiwavelet for fault diagnosis of rolling
Systems Man and Cybernetics: Part B Cybernetics,
IEEE Transactions on Systems, 2007, 37(1) : 70-76.
@@[10] PENG H, LONG F, DING C. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy [J]. IEEE Trans
actions on Pattern Analysis and Machine Intelligence,
bearing[J]. Journal of Xi'an Jiaotong University,
2010,44(3) :77-81.
@@[2]毋文峰,陈小虎,苏勋家.基于经验模式分解的单通 道机械信号盲分离[J].机械工程学报,2011,47 (4): 12-16.
WU Wenfeng, CHEN Xiaohu, SU Xunjia. Blind
source separation of single-channel mechanical signal based on empirical mode decomposition [J]. Journal of
2005, 27(8): 1226-1238.
@@[11] HU Q, YU D, LIUJ, et al. Neighborhood rough set
based heterogeneous feature subset selection [J]. In
formation Sciences, 2008, 178 (18): 3577-3594.
@@[12]胡清华.混合数据知识发现的粗糙计算模型和算法 [D].哈尔滨:哈尔滨工业大学,2008.
@@[13] LIN R, WANG Y, WU C, et al. Developing a busi
ness failure prediction model via RST, GRA and CBR [J]. Expert Systems with Applications, 2009,36 (2) :
Mechanical Engineering, 2011,47(4) : 12-16.
@@[3]汤宝平,李锋,陈仁祥.基于Littlewood-Paley小波支 持向量机的故障诊断[J].振动与冲击,2011,1(30):
128-131.
TANG Baoping, LI Feng, CHEN Renxiang. Fault diagnosis based on Littlewood-Paley wavelet support
vector machine [J]. Journal of Vibration and Shock,
1593-1600.
@@[14] JIANG Y, CHEN J, RUAN X. Fuzzy similarity-based
rough set method for case-based reasoning and its ap
plication in tool selection [J]. International Journal of
Machine Tools and Manufacture, 2006, 46(2) : 107-
2011,1(30) : 128-131.
113.
@@[15] SHIN K, HAN I. Case-based reasoning supported by
genetic algorithms for corporate bond rating [J]. Ex pert Systems with Applications, 1999, 16(2) : 85-95.
@@[4]栗茂林,王孙安,梁霖.利用非线性流形学习的轴承 早期故障特征提取方法[J].西安交通大学学报, 2010, 44 (5): 45-49.
LI Maolin, WANG Sun' an, LIANG Lin. Feature ex
traction for incipient diagnosis of rolling bearings based
@@[16] AHN H, KIM K. Bankruptcy prediction modeling with hybrid case-based reasoning and genetic algo
rithms approach [J]. Applied Soft Computing, 2009,
on nonlinear manifold learning[J]. Journal of Xi'an
Jiaotong University,2010,44(5) :45-99.
9 (2): 599-607.
@@[17] NUNEZ H, SANCHEZMARRE M, CORTES U, et
al. A comparative study on the use of similarity meas ures in case-based reasoning to improve the chssifica tion of environmental system situations [J]. Environ
@@[5]吴元修.神经网络在风电机组机械传动系统故障诊断 中的应用研究[J].制造业自动化,2010(10): 130- 131.
WU Yuanxiu. Application research of the fault diagno
sis on the wind turbine mechanical transmission system
mental Modelling & Software, 2004,19(9): 809-819.
with neural networks [J]. Manufacturing Automation,
滚动轴承故障诊断的案例推理方法
作者:作者单位:刊名:英文刊名:年,卷(期):
付新哲, 张优云, 朱永生, FU Xinzhe, ZHANG Youyun, ZHU Yongsheng西安交通大学机械工程学院,710049,西安西安交通大学学报
Journal of Xi'an Jiaotong University2011,45(11)
本文链接:http://d.g.wanfangdata.com.cn/Periodical_xajtdxxb201111015.aspx
滚动轴承故障诊断的案例推理方法
付新哲张优云
朱永生
西安交通大学机械工程学院,710049,西安
摘要:针对滚动轴承的故障诊断问题,提出了一种采用案例推理(CBR)的诊断方法.为了解决检索
相似案例时案例属性多、人工确定关键属性及其权重困难的问题,提出了一种Filter/Wrapper复合型特征选择算法,用邻域粗糙集算法粗选属性,用遗传算法进一步精选属性和优化权重,并有效地解决了邻域粗糙集算法中需要人工确定邻域大小的问题.以滚动轴承运行时的振动信号为基本信息,建立了滚动轴承案例库,从案例库中检索与问题案例相似的历史案例,并根据这些历史案例来判定问题案例的故障类别.试验结果表明,故障诊断的正确率达到100%,故障位置诊断的正确卒达到93.3%,且算法具有较好的稳定性.
案例推理;滚动轴承;故障诊断
TH17A
0253-987X(2011) 11-0079-06
Rolling Bearing Fault Diagnosis Approach
Based on Case-Based Reasoning
FU Xinzhe ZHANG Youyun ZHU Yongsheng
2011-03-30
f寸新哲(1985-),男,硕士生;张优云(联系人),女,教授.
国家自然科学基
金资助项目(51035007).
]都被用
类型为
l和较高
结论
2010(10) : 130-131.
@@[6] WATSON I. Case-based reasoning is a methodology not a technology [ J ]. Knowledge-Based Systems,
1999, 12 (1/6): 303-308.
@@[7] GUYON I, ELISSEEFF A. An introduction to varia
ble and feature selection [J]. The Journal of Machine
Learning Research, 2003(3): 1157-1182.@@[8] UNCU O, TURKSEN I. A novel feature selection ap
proach: combining feature wrappers and filters [J].
Information Sciences, 2007, 177 (2): 449-466.@@[9] ZHU Z, ONG Y S, DASH M. Wrapper/filter feature selection algorithm using a memetic framework[J].
@@[1]王晓冬,何正嘉,訾艳阳.滚动轴承故障诊断的多小 波谱峭度方法[J].西安交通大学学报,2010,44 (3), 77-81.
WANG Xiaodong, HE Zhengjia, ZI Yanyang. Spectral
kurtosis of multiwavelet for fault diagnosis of rolling
Systems Man and Cybernetics: Part B Cybernetics,
IEEE Transactions on Systems, 2007, 37(1) : 70-76.
@@[10] PENG H, LONG F, DING C. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy [J]. IEEE Trans
actions on Pattern Analysis and Machine Intelligence,
bearing[J]. Journal of Xi'an Jiaotong University,
2010,44(3) :77-81.
@@[2]毋文峰,陈小虎,苏勋家.基于经验模式分解的单通 道机械信号盲分离[J].机械工程学报,2011,47 (4): 12-16.
WU Wenfeng, CHEN Xiaohu, SU Xunjia. Blind
source separation of single-channel mechanical signal based on empirical mode decomposition [J]. Journal of
2005, 27(8): 1226-1238.
@@[11] HU Q, YU D, LIUJ, et al. Neighborhood rough set
based heterogeneous feature subset selection [J]. In
formation Sciences, 2008, 178 (18): 3577-3594.
@@[12]胡清华.混合数据知识发现的粗糙计算模型和算法 [D].哈尔滨:哈尔滨工业大学,2008.
@@[13] LIN R, WANG Y, WU C, et al. Developing a busi
ness failure prediction model via RST, GRA and CBR [J]. Expert Systems with Applications, 2009,36 (2) :
Mechanical Engineering, 2011,47(4) : 12-16.
@@[3]汤宝平,李锋,陈仁祥.基于Littlewood-Paley小波支 持向量机的故障诊断[J].振动与冲击,2011,1(30):
128-131.
TANG Baoping, LI Feng, CHEN Renxiang. Fault diagnosis based on Littlewood-Paley wavelet support
vector machine [J]. Journal of Vibration and Shock,
1593-1600.
@@[14] JIANG Y, CHEN J, RUAN X. Fuzzy similarity-based
rough set method for case-based reasoning and its ap
plication in tool selection [J]. International Journal of
Machine Tools and Manufacture, 2006, 46(2) : 107-
2011,1(30) : 128-131.
113.
@@[15] SHIN K, HAN I. Case-based reasoning supported by
genetic algorithms for corporate bond rating [J]. Ex pert Systems with Applications, 1999, 16(2) : 85-95.
@@[4]栗茂林,王孙安,梁霖.利用非线性流形学习的轴承 早期故障特征提取方法[J].西安交通大学学报, 2010, 44 (5): 45-49.
LI Maolin, WANG Sun' an, LIANG Lin. Feature ex
traction for incipient diagnosis of rolling bearings based
@@[16] AHN H, KIM K. Bankruptcy prediction modeling with hybrid case-based reasoning and genetic algo
rithms approach [J]. Applied Soft Computing, 2009,
on nonlinear manifold learning[J]. Journal of Xi'an
Jiaotong University,2010,44(5) :45-99.
9 (2): 599-607.
@@[17] NUNEZ H, SANCHEZMARRE M, CORTES U, et
al. A comparative study on the use of similarity meas ures in case-based reasoning to improve the chssifica tion of environmental system situations [J]. Environ
@@[5]吴元修.神经网络在风电机组机械传动系统故障诊断 中的应用研究[J].制造业自动化,2010(10): 130- 131.
WU Yuanxiu. Application research of the fault diagno
sis on the wind turbine mechanical transmission system
mental Modelling & Software, 2004,19(9): 809-819.
with neural networks [J]. Manufacturing Automation,
滚动轴承故障诊断的案例推理方法
作者:作者单位:刊名:英文刊名:年,卷(期):
付新哲, 张优云, 朱永生, FU Xinzhe, ZHANG Youyun, ZHU Yongsheng西安交通大学机械工程学院,710049,西安西安交通大学学报
Journal of Xi'an Jiaotong University2011,45(11)
本文链接:http://d.g.wanfangdata.com.cn/Periodical_xajtdxxb201111015.aspx