采用非相关字典学习的滚动轴承故障诊断方法
|
摘要
针对轴承振动信号中早期故障特征难以识别的问题,提出了利用非相关字典学习稀疏提取微弱冲击特征,进而完成故障诊断的方法。字典的构造是影响稀疏表示算法性能的关键步骤,而传统字典学习方法构造的冗余字典,原子之间具有很强的相关性,不足以表现信号不同的结构特性,也不利于信号准确稀疏重构,进而影响了冲击故障特征信号的提取。因此,在K均值奇异值分解算法(K-SVD)的基础上加入了原子解相关的步骤,形成了非相关字典学习算法(INK-SVD)。采用INK-SVD算法在含噪振动信号段样本中,学习构造低相关性自适应字典;在此基础上,利用稀疏表示方法准确提取冲击故障特征,从而实现更准确的轴承故障诊断。通过仿真分析及实验数据分析,与传统字典学习方法相比,该方法稀疏系数恢复精确度更高,重构信号的包络解调谱更有利于故障特征的辨识,从而验证了该方法的有效性。
To identify the weak fault features of bearing vibration signals at the early stage, incoherent dictionary learning methods are utilized to extract impact features of the signals and diagnose the fault. The dictionary construction is a key step that determines the performance of the sparse representation algorithm. The redundant dictionaries constructed by the traditional dictionary learning methods, however, have a great correlation between atoms. They are not enough to represent different structural characteristics of the signals and are not conducive to the accurate sparse reconstruction of the signals. Therefore, the incoherent dictionary learning method(INK-SVD) is adopted to reconstruct the adaptive dictionaries with low correlation. The low correlation dictionary is learned adaptively in the samples of noisy vibration by the INK-SVD, and the impact fault features are extracted accurately with sparse representation algorithm, so as to achieve more precise bearing fault diagnosis. In terms of the simulation and experiment analysis, the proposed method is able to obtain more accurate sparse coefficients compared with classical dictionary learning methods. Therefore, the envelope demodulation spectrum of the reconstructed signal is more conducive to fault feature identification, which verifies the effectiveness of the method.
To identify the weak fault features of bearing vibration signals at the early stage, incoherent dictionary learning methods are utilized to extract impact features of the signals and diagnose the fault. The dictionary construction is a key step that determines the performance of the sparse representation algorithm. The redundant dictionaries constructed by the traditional dictionary learning methods, however, have a great correlation between atoms. They are not enough to represent different structural characteristics of the signals and are not conducive to the accurate sparse reconstruction of the signals. Therefore, the incoherent dictionary learning method(INK-SVD) is adopted to reconstruct the adaptive dictionaries with low correlation. The low correlation dictionary is learned adaptively in the samples of noisy vibration by the INK-SVD, and the impact fault features are extracted accurately with sparse representation algorithm, so as to achieve more precise bearing fault diagnosis. In terms of the simulation and experiment analysis, the proposed method is able to obtain more accurate sparse coefficients compared with classical dictionary learning methods. Therefore, the envelope demodulation spectrum of the reconstructed signal is more conducive to fault feature identification, which verifies the effectiveness of the method.
引文
[1] 王国彪,何正嘉,陈雪峰,等.机械故障诊断基础研究“何去何从” [J].机械工程学报,2013,49(1):63-72.WANG Guobiao,HE Zhengjia,CHEN Xuefeng,et al.Basic research on machinery fault diagnosis:what is the prescription [J].Chinese Journal of Mechanical Engineering,2013,49(1):63-72.
[2] 张晗,杜朝辉,方作为,等.基于稀疏分解理论的航空发动机轴承故障诊断 [J].机械工程学报,2015(1):97-105.ZHANG Han,DU Zhaohui,FANG Zuowei,et al.Sparse decomposition based aero-engine’s bearing fault diagnosis [J].Chinese Journal of Mechanical Engineering,2015(1):97-105.
[3] 张西宁,唐春华,周融通,等.一种自适应形态滤波算法及其在轴承故障诊断中的应用 [J].西安交通大学学报,2018,52(12):1-8.ZHANG Xining,TANG Chunhua,ZHOU Rongtong.Adaptive morphological filtering algorithm with applications in bearing fault diagnosis [J].Journal of Xi’an Jiaotong University,2018,52(12):1-8.
[4] FAN W,CAI G,ZHU Z K,et al.Sparse representation of transients in wavelet basis and its application in gearbox fault feature extraction [J].Mechanical Systems and Signal Processing,2015,56:230-245.
[5] 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 bearing [J].Journal of Xi’an Jiaotong University,2010,44(3):77-81.
[6] CHEN X,DU Z,LI J,et al.Compressed sensing based on dictionary learning for extracting impulse components [J].Signal Processing,2014,96:94-109.
[7] FENG Z,LIANG M.Complex signal analysis for planetary gearbox fault diagnosis via shift invariant dictionary learning [J].Measurement,2016,90:382-395.
[8] TROPP J A.Greed is good:algorithmic results for sparse approximation [J].IEEE Transactions on Information Theory,2004,50(10):2231-2242.
[9] OLSHAUSEN B A,FIELD D J.Natural image statistics and efficient coding [J].Network:computation in Neural Systems,1996,7(2):333-339.
[10] ENGAN K,AASE S O,HUS?Y J H.Multi-frame compression:theory and design [J].Signal Processing,2000,80(10):2121-2140.
[11] AHARON M,ELAD M,BRUCKSTEIN A.K-SVD:an algorithm for designing overcomplete dictionaries for sparse representation [J].IEEE Transactions on Signal Processing,2006,54(11):4311-4322.
[12] MAILH B,BARCHIESI D,PLUMBLEY M D.INK-SVD:learning incoherent dictionaries for sparse representations [C]//Proceedings of the IEEE International Conference on Acoustics,Speech and Signal Processing.Piscataway,NJ,USA:IEEE,2012:3573-3576.
[13] MALLAT S G,ZHANG Z.Matching pursuits with time-frequency dictionaries [J].IEEE Transactions on Signal Processing,1994,41(12):3397-3415.
[14] VU T H,MOUSAVI H S,MONGA V.Adaptive matching pursuit for sparse signal recovery [C]//IEEE International Conference on Acoustics.Piscataway,NJ,USA:IEEE,2017:4331-4335.
[15] TROPP J A,GILBERT A C.Signal recovery from random measurements via orthogonal matching pursuit [J].IEEE Transactions on Information Theory,2007,53(12):4655-4666.
[16] BEI L,YING S,LI G,et al.Gesture recognition based on modified adaptive orthogonal matching pursuit algorithm [J].Cluster Computing,2017(3):1-10.
[17] CHEN S S,DONOHO D L,SAUNDERS M A.Atomic decomposition by basis pursuit [J].SIAM Review,2001,43(1):129-159.
[18] TROPP J A.Greed is good:algorithmic results for sparse approximation [J].IEEE Transactions on Information Theory,2004,50(10):2231-2242.
[19] 王君地.基于稀疏表示的音频修复算法研究 [D].成都:电子科技大学,2016:25-30.
[2] 张晗,杜朝辉,方作为,等.基于稀疏分解理论的航空发动机轴承故障诊断 [J].机械工程学报,2015(1):97-105.ZHANG Han,DU Zhaohui,FANG Zuowei,et al.Sparse decomposition based aero-engine’s bearing fault diagnosis [J].Chinese Journal of Mechanical Engineering,2015(1):97-105.
[3] 张西宁,唐春华,周融通,等.一种自适应形态滤波算法及其在轴承故障诊断中的应用 [J].西安交通大学学报,2018,52(12):1-8.ZHANG Xining,TANG Chunhua,ZHOU Rongtong.Adaptive morphological filtering algorithm with applications in bearing fault diagnosis [J].Journal of Xi’an Jiaotong University,2018,52(12):1-8.
[4] FAN W,CAI G,ZHU Z K,et al.Sparse representation of transients in wavelet basis and its application in gearbox fault feature extraction [J].Mechanical Systems and Signal Processing,2015,56:230-245.
[5] 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 bearing [J].Journal of Xi’an Jiaotong University,2010,44(3):77-81.
[6] CHEN X,DU Z,LI J,et al.Compressed sensing based on dictionary learning for extracting impulse components [J].Signal Processing,2014,96:94-109.
[7] FENG Z,LIANG M.Complex signal analysis for planetary gearbox fault diagnosis via shift invariant dictionary learning [J].Measurement,2016,90:382-395.
[8] TROPP J A.Greed is good:algorithmic results for sparse approximation [J].IEEE Transactions on Information Theory,2004,50(10):2231-2242.
[9] OLSHAUSEN B A,FIELD D J.Natural image statistics and efficient coding [J].Network:computation in Neural Systems,1996,7(2):333-339.
[10] ENGAN K,AASE S O,HUS?Y J H.Multi-frame compression:theory and design [J].Signal Processing,2000,80(10):2121-2140.
[11] AHARON M,ELAD M,BRUCKSTEIN A.K-SVD:an algorithm for designing overcomplete dictionaries for sparse representation [J].IEEE Transactions on Signal Processing,2006,54(11):4311-4322.
[12] MAILH B,BARCHIESI D,PLUMBLEY M D.INK-SVD:learning incoherent dictionaries for sparse representations [C]//Proceedings of the IEEE International Conference on Acoustics,Speech and Signal Processing.Piscataway,NJ,USA:IEEE,2012:3573-3576.
[13] MALLAT S G,ZHANG Z.Matching pursuits with time-frequency dictionaries [J].IEEE Transactions on Signal Processing,1994,41(12):3397-3415.
[14] VU T H,MOUSAVI H S,MONGA V.Adaptive matching pursuit for sparse signal recovery [C]//IEEE International Conference on Acoustics.Piscataway,NJ,USA:IEEE,2017:4331-4335.
[15] TROPP J A,GILBERT A C.Signal recovery from random measurements via orthogonal matching pursuit [J].IEEE Transactions on Information Theory,2007,53(12):4655-4666.
[16] BEI L,YING S,LI G,et al.Gesture recognition based on modified adaptive orthogonal matching pursuit algorithm [J].Cluster Computing,2017(3):1-10.
[17] CHEN S S,DONOHO D L,SAUNDERS M A.Atomic decomposition by basis pursuit [J].SIAM Review,2001,43(1):129-159.
[18] TROPP J A.Greed is good:algorithmic results for sparse approximation [J].IEEE Transactions on Information Theory,2004,50(10):2231-2242.
[19] 王君地.基于稀疏表示的音频修复算法研究 [D].成都:电子科技大学,2016:25-30.