基于连续隐马尔可夫的滚动轴承故障诊断
|
摘要
针对滚动轴承发生故障时呈现出的循环平稳特征,提出基于二阶循环平稳的谱相关密度组合切片能量熵-连续隐马尔可夫(SEESCD-CHMM)的滚动轴承故障诊断方法.首先用SEESCD分析方法对滚动轴承4种工作状态(正常、内圈故障、外圈故障和滚动体故障)的数据进行特征提取组成训练特征向量;然后用训练特征向量对CHMM进行模型训练,取得CHMM模型的最优参数;最后用谱SEESCD分析方法对测试数据进行特征提取得到测试特征向量,用训练好的隐马尔科夫(HMM)模型对测试特征向量进行诊断,取得了准确率较高的诊断结果.
Taking advantage of the property of cyclostationarity when fault arises in rolling bearing,the paper proposes the fault diagnosis method of rolling bearing based on slice energy entropy-continuous hidden Markov model(SEESCD-CHMM).Firstly,use the method of SEESCD to extract the rolling bearing four states'(normal,inner race fault,outer race fault and ball element fault)data to form the training feature vectors.Then use the training feature vectors to train the model of CHMM and get the optimal parameters of CHMM.At last,use the SEESCD to extract the test data to form the test feature vectors.Use the trained CHMM model to diagnose the test feature vectors and perfect diagnosis results are got.
Taking advantage of the property of cyclostationarity when fault arises in rolling bearing,the paper proposes the fault diagnosis method of rolling bearing based on slice energy entropy-continuous hidden Markov model(SEESCD-CHMM).Firstly,use the method of SEESCD to extract the rolling bearing four states'(normal,inner race fault,outer race fault and ball element fault)data to form the training feature vectors.Then use the training feature vectors to train the model of CHMM and get the optimal parameters of CHMM.At last,use the SEESCD to extract the test data to form the test feature vectors.Use the trained CHMM model to diagnose the test feature vectors and perfect diagnosis results are got.
引文
[1]CAPDESSUS C,SIDAHMED M,LACOUME J L.Cyclostationary processes:application in gear faults early diagnosis[J].Mechanical Systems and Signal Processing,2000,14(3):371-385.
[2]ANTONI J.Cyclic spectral analysis of rolling-element bearing signals:facts and fictions[J].Journal of Sound and Vibration,2007,304:497-529.
[3]RAAD A,ANTONI J,SIDAHMED M.Indicators of cyclostationarity:theory and application to gear fault monitoring[J].Mechanical Systems and Signal Processing,2008,22:574-587.
[4]MIAO Q,MAKIS V.Condition monitoring and classification of rotating machinery using wavelets and hidden Markov models[J].Mechanical Systems and Signal Processing,2007,21:840-855.
[5]LEE J M,KIM S J,HWANG Y,et al.Diagnosis of mechanical fault signals using continuous hidden Markov model[J].Journal of Sound and Vibration,2004,276:1065-1080.
[6]毕果,陈进,周福昌,等.调幅信号谱相关密度分析中白噪声影响的研究[J].振动与冲击,2006,25(2):75-78.BI G,CHEN J,ZHOU F C,et al.Influence of the noise on spectral correlation density analysis of AM signal[J].Journal of Vibration and Shock,2006,25(2):75-78.
[7]申弢,黄树红,韩守木,等.旋转机械振动信号的信息熵特征[J].机械工程学报,2001,37(6):94-98.SHEN T,HUANG S H,HAN S M,et al.Extracting information entropy features for rotating machinery vibration signals[J].Chinese Journal of Mechanical Engineering,2001,37(6):94-98.
[8]JARDINE A K S,LIN D M,BANJEVIC D.A review on machinery diagnostics and prognostics implementing condition-based maintenance[J].Mechanical Systems and Signal Processing,2006,20:1483-1510.
[2]ANTONI J.Cyclic spectral analysis of rolling-element bearing signals:facts and fictions[J].Journal of Sound and Vibration,2007,304:497-529.
[3]RAAD A,ANTONI J,SIDAHMED M.Indicators of cyclostationarity:theory and application to gear fault monitoring[J].Mechanical Systems and Signal Processing,2008,22:574-587.
[4]MIAO Q,MAKIS V.Condition monitoring and classification of rotating machinery using wavelets and hidden Markov models[J].Mechanical Systems and Signal Processing,2007,21:840-855.
[5]LEE J M,KIM S J,HWANG Y,et al.Diagnosis of mechanical fault signals using continuous hidden Markov model[J].Journal of Sound and Vibration,2004,276:1065-1080.
[6]毕果,陈进,周福昌,等.调幅信号谱相关密度分析中白噪声影响的研究[J].振动与冲击,2006,25(2):75-78.BI G,CHEN J,ZHOU F C,et al.Influence of the noise on spectral correlation density analysis of AM signal[J].Journal of Vibration and Shock,2006,25(2):75-78.
[7]申弢,黄树红,韩守木,等.旋转机械振动信号的信息熵特征[J].机械工程学报,2001,37(6):94-98.SHEN T,HUANG S H,HAN S M,et al.Extracting information entropy features for rotating machinery vibration signals[J].Chinese Journal of Mechanical Engineering,2001,37(6):94-98.
[8]JARDINE A K S,LIN D M,BANJEVIC D.A review on machinery diagnostics and prognostics implementing condition-based maintenance[J].Mechanical Systems and Signal Processing,2006,20:1483-1510.