基于移不变字典学习和稀疏编码的滚动轴承故障识别算法
|
摘要
针对现有旋转机械故障识别算法过度依赖专家先验知识的问题,提出了一种基于移不变字典学习和稀疏编码(SIDL-SC)的自适应故障识别算法。将不同故障状态下的振动信号进行分段和平滑预处理以降低数据处理复杂度;将加入自适应惩罚因子的移不变字典学习算法用于提取不同故障状态下的移不变基函数;利用高效的特征符号搜索算法求解待识别信号在不同基函数下的稀疏系数以实现对待识别信号的重构。最后,以重构残差作为对该信号故障状态识别的判断依据。滚动轴承振动数据库和实测航空发动机振动信号的实验结果表明,该算法相较于现有算法具有更高的故障识别准确率,在实际中具有较强的可行性。
According to current algorithms for rotating machines largely depending on expert prior knowledge,this paper proposed an adaptive fault recognition algorithm based on shift invariant dictionary learning and sparse coding. Firstly,it segmented and smoothed vibration signals to decrease the complexity. Then,it used shift invariant dictionary learning with adaptive penalty factor to learn shift invariant bases in different fault states. After that,it used an efficient sparse coefficient solver called feature sign search for reconstructing signal to be recognized. Lastly,residual was an evidence to determining fault state the signal belonging to. In the experiments of rolling bearing datasets and vibration signals of real aero-engine demonstrate its higher accuracy than up-to-date algorithms and feasibility for practical applications.
According to current algorithms for rotating machines largely depending on expert prior knowledge,this paper proposed an adaptive fault recognition algorithm based on shift invariant dictionary learning and sparse coding. Firstly,it segmented and smoothed vibration signals to decrease the complexity. Then,it used shift invariant dictionary learning with adaptive penalty factor to learn shift invariant bases in different fault states. After that,it used an efficient sparse coefficient solver called feature sign search for reconstructing signal to be recognized. Lastly,residual was an evidence to determining fault state the signal belonging to. In the experiments of rolling bearing datasets and vibration signals of real aero-engine demonstrate its higher accuracy than up-to-date algorithms and feasibility for practical applications.
引文
[1]朱会杰,王新晴,芮挺,等.多尺度移不变稀疏编码及其在机械故障诊断中的应用[J].北京理工大学学报,2016,36(1):19-24.(Zhu Huijie,Wang Xinqing,Rui Ting,et al. Multi scale shift invariant sparse coding for robust machinery diagnosis[J]. Transactions of Beijing Insititute of Technology,2016,36(1):19-24.)
[2] Janssens O,Slavkovikj V,Vervisch B,et al. Convolutional neural network based fault detection for rotating machinery[J].Journal of Sound&Vibration,2016,377(9):331-345.
[3] Harmouche J,Delpha C,Diallo D. Improved fault diagnosis of ball bearings based on the global spectrum of vibration signals[J]. IEEE Trans on Energy Conversion,2015,30(1):376-383.
[4]王录雁,王强,张梅军,等.基于EMD的滚动轴承故障灰色诊断方法[J].振动与冲击,2014,33(3):197-202.(Wang Luyan,Wang Qiang,Zhang Meijun,et al. A grey fault diagnosis method for rolling bearings based on EMD[J]. Journal of Vibration and Shock,2014,33(3):197-202.)
[5]蔡剑华,胡惟文,王先春.基于高阶统计量的滚动轴承故障诊断方法[J].振动、测试与诊断,2013,33(2):298-301.(Cai Jianhua,Hu Weiwen,Wang Xianchun. Roller bearing fault diagnosis based on higher-order statistics[J]. Journal of Vibration,Measurement&Diagnosis,2013,33(2):298-301.)
[6] Wright J,Yang A Y,Ganesh A,et al. Robust face recognition via sparse representation[J]. IEEE Trans on Pattern Analysis&Machine Intelligence,2009,31(2):210-227.
[7]张新鹏,胡茑庆,程哲,等.基于压缩感知的振动数据修复方法[J].物理学报,2014,63(20):115-124.(Zhang Xinpeng,Hu Niaoqing,Cheng Zhe,et al. Vibration data recovery based on compressed sensing[J]. Acta Physica Sinica,2014,63(20):115-124.)
[8]郭亮,高宏力,黄海凤,等.基于压缩感知理论的时变信号压缩技术[J].西南交通大学学报,2015,50(3):511-516.(Guo Liang,Gao Hongli,Huang Haifeng,et al. Time-varing signal compression technology based on compressed sensing[J]. Journal of Southwest Jiaotong University,2015,50(3):511-516.)
[9]彭向东,张华,刘继忠.基于过完备字典的体域网压缩感知心电重构[J].自动化学报,2014,40(7):1421-1432.(Peng Xiangdong,Zhang Hua,Liu Jizhong. ECG reconstruction of body sensor network using compressed sensing based on overcomplete dictionary[J]. ACTA Automatica Sinica,2014,40(7):1421-1432.)
[10]Aharon M,Elad M,Bruckstdin A M,et al. K-SVD:an algorithm for designing overcomplete dictionaries for sparse representation[J].IEEE Trans on Signal Processing,2006,54(11):4311-4322.
[11] Smith E C,Lewicki M S. Efficient auditory coding[J]. Nature,2006,439(7079):978-982.
[12]Mrup M,Schmidt M N,Hansen L K. Shift invariant sparse coding of image and music data[R]. 2007.
[13]Tang Haifeng,Chen Jin,Dong Guangming. Sparse representation based latent components analysis for machinery weak fault detection[J]. Mechanical Systems&Signal Processing,2014,46(2):373-388.
[14]Grosse R,Raina R,Kwong H,et al. Shift-invariant sparse coding for audio classification[C]//Proc of Conference on Uncertainty in AI.Vancouver:AUAI Press,2007:149-158.
[15]Rubinstein R,Zibulevsky M,Elad M. Efficient implementation of the K-SVD algorithm using batch orthogonal matching pursuit[M]//CS Technion,2011.
[16] Lee H,Battle A,Raina R,et al. Efficient sparse coding algorithms[C]//Advances in Neural Information Processing Systems.2006:801-808.
[17] http://csegroups. case. edu/bearingdatacenter/pages/download-data-file[EB/OL].
[18] Liu Haining,Liu Chengliang,Huang Yixiang. Adaptive feature extraction using sparse coding for machinery fault diagnosis[J]. Mechanical Systems and Signal Processing,2011,25(2):558-574.
[19]Chen Zhiqiang,Li Chuan,Sanchez R V. Gearbox fault identification and classification with convolutional neural networks[J]. Shock&Vibration,2015,2015(2):1-10.
[2] Janssens O,Slavkovikj V,Vervisch B,et al. Convolutional neural network based fault detection for rotating machinery[J].Journal of Sound&Vibration,2016,377(9):331-345.
[3] Harmouche J,Delpha C,Diallo D. Improved fault diagnosis of ball bearings based on the global spectrum of vibration signals[J]. IEEE Trans on Energy Conversion,2015,30(1):376-383.
[4]王录雁,王强,张梅军,等.基于EMD的滚动轴承故障灰色诊断方法[J].振动与冲击,2014,33(3):197-202.(Wang Luyan,Wang Qiang,Zhang Meijun,et al. A grey fault diagnosis method for rolling bearings based on EMD[J]. Journal of Vibration and Shock,2014,33(3):197-202.)
[5]蔡剑华,胡惟文,王先春.基于高阶统计量的滚动轴承故障诊断方法[J].振动、测试与诊断,2013,33(2):298-301.(Cai Jianhua,Hu Weiwen,Wang Xianchun. Roller bearing fault diagnosis based on higher-order statistics[J]. Journal of Vibration,Measurement&Diagnosis,2013,33(2):298-301.)
[6] Wright J,Yang A Y,Ganesh A,et al. Robust face recognition via sparse representation[J]. IEEE Trans on Pattern Analysis&Machine Intelligence,2009,31(2):210-227.
[7]张新鹏,胡茑庆,程哲,等.基于压缩感知的振动数据修复方法[J].物理学报,2014,63(20):115-124.(Zhang Xinpeng,Hu Niaoqing,Cheng Zhe,et al. Vibration data recovery based on compressed sensing[J]. Acta Physica Sinica,2014,63(20):115-124.)
[8]郭亮,高宏力,黄海凤,等.基于压缩感知理论的时变信号压缩技术[J].西南交通大学学报,2015,50(3):511-516.(Guo Liang,Gao Hongli,Huang Haifeng,et al. Time-varing signal compression technology based on compressed sensing[J]. Journal of Southwest Jiaotong University,2015,50(3):511-516.)
[9]彭向东,张华,刘继忠.基于过完备字典的体域网压缩感知心电重构[J].自动化学报,2014,40(7):1421-1432.(Peng Xiangdong,Zhang Hua,Liu Jizhong. ECG reconstruction of body sensor network using compressed sensing based on overcomplete dictionary[J]. ACTA Automatica Sinica,2014,40(7):1421-1432.)
[10]Aharon M,Elad M,Bruckstdin A M,et al. K-SVD:an algorithm for designing overcomplete dictionaries for sparse representation[J].IEEE Trans on Signal Processing,2006,54(11):4311-4322.
[11] Smith E C,Lewicki M S. Efficient auditory coding[J]. Nature,2006,439(7079):978-982.
[12]Mrup M,Schmidt M N,Hansen L K. Shift invariant sparse coding of image and music data[R]. 2007.
[13]Tang Haifeng,Chen Jin,Dong Guangming. Sparse representation based latent components analysis for machinery weak fault detection[J]. Mechanical Systems&Signal Processing,2014,46(2):373-388.
[14]Grosse R,Raina R,Kwong H,et al. Shift-invariant sparse coding for audio classification[C]//Proc of Conference on Uncertainty in AI.Vancouver:AUAI Press,2007:149-158.
[15]Rubinstein R,Zibulevsky M,Elad M. Efficient implementation of the K-SVD algorithm using batch orthogonal matching pursuit[M]//CS Technion,2011.
[16] Lee H,Battle A,Raina R,et al. Efficient sparse coding algorithms[C]//Advances in Neural Information Processing Systems.2006:801-808.
[17] http://csegroups. case. edu/bearingdatacenter/pages/download-data-file[EB/OL].
[18] Liu Haining,Liu Chengliang,Huang Yixiang. Adaptive feature extraction using sparse coding for machinery fault diagnosis[J]. Mechanical Systems and Signal Processing,2011,25(2):558-574.
[19]Chen Zhiqiang,Li Chuan,Sanchez R V. Gearbox fault identification and classification with convolutional neural networks[J]. Shock&Vibration,2015,2015(2):1-10.