柴油机振动信号快速稀疏分解与二维特征编码
|
摘要
针对柴油机故障诊断方法中的信号时频表征及特征提取问题,提出一种基于振动信号快速稀疏分解与二维时频特征编码识别的柴油机智能故障诊断方法。首先,为了获得时、频聚集性优良的时频图像,提出一种随分解残差信号自适应更新Gabor字典的改进匹配追踪(adaptive matching pursuit,简称AMP)算法,利用AMP算法将柴油机振动信号分解后叠加各原子分量的Wigner-Ville分布,获取原信号的稀疏分解时频图像;然后,为提取时频图像的特征参量,提出了双向二维非负矩阵分解(two-directional,2-dimensional non-negative matrix factorization,简称TD2DNMF)算法,用于对时频图像的幅值矩阵进行特征编码,获取蕴含在时频图像内部的低维特征,并利用最近邻分类器实现了时频图像的自动分类识别。将提出的方法应用于4种不同状态柴油机气门故障的诊断试验中,结果表明,该方法能够获得无交叉项干扰、聚集性好的时频图像,使各时频分量的物理意义更加明确,并改进了传统图像模式识别中的特征参数提取方法,是一种有效的柴油机故障诊断方法。
In view of the interference of cross-term in diesel engine vibration signal time-frequency distribution and the difficulty in feature extraction,a new diesel engine intelligent fault diagnosis method based on rapid vibration signal sparse decomposition and two-dimensional time-frequency feature encoding recognition are proposed.First,a modified matching pursuit method called adaptive matching pursuit(AMP)whose dictionary can be updated according to the residual signal adaptively in the decomposition is put forward to obtain the vibration time-frequency images with good time-frequency aggregation.Then,the signals are decomposed into a series of atoms based on AMP algorithm and the time-frequency distribution of the original signals are obtained based on the Wigner-Ville distribution of these atoms.The feature coding of the time-frequency image amplitude matrix is captured using a two-directional two-dimensional NMF(TD2 DNMF)algorithm,which can acquire the low dimensional characteristics contained within the higher dimensional time-frequency image.Finally,the nearest neighbor classifier is used to realize the automatic classification of time-frequency image recognition.The proposed method is applied to extract the fault features from four different state diesel engine valve faults,and the results verify that this method works well in eliminating the interference of cross terms in diesel engine vibration signal time-frequency distribution,and it improves the traditional image characteristic parameter extraction method of pattern recognition,the quick and effective fault diagnosis of diesel engine valve is realized by this proposed method.
In view of the interference of cross-term in diesel engine vibration signal time-frequency distribution and the difficulty in feature extraction,a new diesel engine intelligent fault diagnosis method based on rapid vibration signal sparse decomposition and two-dimensional time-frequency feature encoding recognition are proposed.First,a modified matching pursuit method called adaptive matching pursuit(AMP)whose dictionary can be updated according to the residual signal adaptively in the decomposition is put forward to obtain the vibration time-frequency images with good time-frequency aggregation.Then,the signals are decomposed into a series of atoms based on AMP algorithm and the time-frequency distribution of the original signals are obtained based on the Wigner-Ville distribution of these atoms.The feature coding of the time-frequency image amplitude matrix is captured using a two-directional two-dimensional NMF(TD2 DNMF)algorithm,which can acquire the low dimensional characteristics contained within the higher dimensional time-frequency image.Finally,the nearest neighbor classifier is used to realize the automatic classification of time-frequency image recognition.The proposed method is applied to extract the fault features from four different state diesel engine valve faults,and the results verify that this method works well in eliminating the interference of cross terms in diesel engine vibration signal time-frequency distribution,and it improves the traditional image characteristic parameter extraction method of pattern recognition,the quick and effective fault diagnosis of diesel engine valve is realized by this proposed method.
引文
[1]Komorska I.Adaptive model of engine vibration signal for diagnostics of mechanical defects[J].Mechanics,2013,19(3):301-305.
[2]沈虹,赵红东,梅检民,等.基于高阶累积量图像特征的柴油机故障诊断研究[J].振动与冲击,2015,34(11):133-138.Shen Hong,Zhao Hongdong,Mei Jianmin,et al.Diesel engine fault diagnosis based on high-order cumulant image features[J].Journal of Vibration and Shock,2015,34(11):133-138.(in Chinese)
[3]刘昱,张俊红,毕凤荣,等.基于Wigner分布和分形维数的柴油机故障诊断[J].振动、测试与诊断,2016,36(2):240-245.Liu Yu,Zhang Junhong,Bi Fengrong,et al.Study on fault diagnosis of diesel valve trains based on Wigner distribution and fractal dimension[J].Journal of Vibration,Measurement&Diagnosis,2016,36(2):240-245.(in Chinese)
[4]蔡艳平,李艾华,王涛,等.基于时频谱图与图像分割的柴油机故障诊断[J].内燃机学报,2011,29(2):181-186.Cai Yanping,Li Aihua,Wang Tao,et al.Diesel engine fault diagnosis based on time-frequency spectrum image and image segmentation[J].Transactions of CSICE,2011,29(2):181-186.(in Chinese)
[5]蔡艳平,李艾华,王涛,等.基于EMD-Wigner-Ville的内燃机振动时频分析[J].振动工程学报,2010,23(4):430-437.Cai Yanping,Li Aihua,Wang Tao,et al.Engine vibration time-frequency analysis based on EMD-Wigner-Ville[J].Journal of Vibration Engineering,2010,23(4):430-437.(in Chinese)
[6]Feng Zhipeng,Liang Min,Chu Fulei.Recent advances in time-frequency analysis methods for machinery fault diagnosis:a review with application examples[J].Mechanical Systems and Signal Processing,2013,38(1):165-205.
[7]Subhash C K S,Ashutosh M,Vinay S,et al.Comparison of matching pursuit algorithm with other signal processing techniques for computation of the timefrequency power spectrum of Brain Signals[J].Neurosci,2016,36(12):3399-3408.
[8]Yang Yongsheng,Ming Anbo,Zhang Youyun,et al.Discriminative non-negative matrix factorization(DNMF)and its application to the fault diagnosis of diesel engine[J].Mechanical Systems and Signal Processing,2017,10(95):158-171.
[9]梁霖,栗茂林,李利邦,等.基于非负矩阵分解的单通道故障特征分离方法[J].振动、测试与诊断,2016,36(5):835-840.Liang lin,Li Maolin,Li Libang,et al.Separation of fault features from a single channel mechanical signal using non-negative matrix factorization[J].Journal of Vibration,Measurement&Diagnosis,2016,36(5):835-840.(in Chinese)
[10]Zhang Daoqiang,Chen Songcan,Zhou Zhihua.Twodimensional non-negative matrix factorization for face representation and recognition[J].Analysis and Modelling of Faces and Gestures,2005,3723:350-363.
[11]Gu Quanquan,Zhou Jie.Two dimensional nonnegative matrix factorization[C]∥16th IEEE International Conference on Image Processing.Cairo,Egypt:IEEE,2009:2069-2072.
[12]高宏娟.基于NMF改进算法的人脸识别仿真研究[J].计算机仿真,2011,28(12):231-235,303.Gao Hongjuan.Research and simulation of face recognition based on nmf and its improvements[J].Computer Simulation,2011,28(12):231-235,303.(in Chinese)
[13]张焱,汤宝平,刘自然,等.时频表示特征约简的旋转机械故障特征提取方法[J].振动工程学报,2015,28(1):156-163.Zhang Yan,Tang Baoping,Liu Ziran,et al.Rotating machine fault feature extraction based on reduced time frequency representation[J].Journal of Vibration Engineering,2015,28(1):156-163.(in Chinese)
[14]李兵,米双山,刘鹏远,等.二维非负矩阵分解在齿轮故障诊断中的应用[J].振动、测试与诊断,2012,32(5):836-840.Li Bing,Mi Shuangshan,Liu Pengyuan,et al.Application of two-dimensional non-negative matrix factorization for gear fault diagnosis[J].Journal of Vibration,Measurement&Diagnosis,2012,32(5):836-840.(in Chinese)
[15]Mallat S,Zhang Zhifeng.Matching pursuits with time-frequency dictionaries[J].IEEE Transactions on Signal Processing,1993,41(12):3397-3415.
[16]Lee D D,Seung H S.Learning the parts of objects by non-negative matrix factorization[J].Nature,1999,401(21):788-791.
[2]沈虹,赵红东,梅检民,等.基于高阶累积量图像特征的柴油机故障诊断研究[J].振动与冲击,2015,34(11):133-138.Shen Hong,Zhao Hongdong,Mei Jianmin,et al.Diesel engine fault diagnosis based on high-order cumulant image features[J].Journal of Vibration and Shock,2015,34(11):133-138.(in Chinese)
[3]刘昱,张俊红,毕凤荣,等.基于Wigner分布和分形维数的柴油机故障诊断[J].振动、测试与诊断,2016,36(2):240-245.Liu Yu,Zhang Junhong,Bi Fengrong,et al.Study on fault diagnosis of diesel valve trains based on Wigner distribution and fractal dimension[J].Journal of Vibration,Measurement&Diagnosis,2016,36(2):240-245.(in Chinese)
[4]蔡艳平,李艾华,王涛,等.基于时频谱图与图像分割的柴油机故障诊断[J].内燃机学报,2011,29(2):181-186.Cai Yanping,Li Aihua,Wang Tao,et al.Diesel engine fault diagnosis based on time-frequency spectrum image and image segmentation[J].Transactions of CSICE,2011,29(2):181-186.(in Chinese)
[5]蔡艳平,李艾华,王涛,等.基于EMD-Wigner-Ville的内燃机振动时频分析[J].振动工程学报,2010,23(4):430-437.Cai Yanping,Li Aihua,Wang Tao,et al.Engine vibration time-frequency analysis based on EMD-Wigner-Ville[J].Journal of Vibration Engineering,2010,23(4):430-437.(in Chinese)
[6]Feng Zhipeng,Liang Min,Chu Fulei.Recent advances in time-frequency analysis methods for machinery fault diagnosis:a review with application examples[J].Mechanical Systems and Signal Processing,2013,38(1):165-205.
[7]Subhash C K S,Ashutosh M,Vinay S,et al.Comparison of matching pursuit algorithm with other signal processing techniques for computation of the timefrequency power spectrum of Brain Signals[J].Neurosci,2016,36(12):3399-3408.
[8]Yang Yongsheng,Ming Anbo,Zhang Youyun,et al.Discriminative non-negative matrix factorization(DNMF)and its application to the fault diagnosis of diesel engine[J].Mechanical Systems and Signal Processing,2017,10(95):158-171.
[9]梁霖,栗茂林,李利邦,等.基于非负矩阵分解的单通道故障特征分离方法[J].振动、测试与诊断,2016,36(5):835-840.Liang lin,Li Maolin,Li Libang,et al.Separation of fault features from a single channel mechanical signal using non-negative matrix factorization[J].Journal of Vibration,Measurement&Diagnosis,2016,36(5):835-840.(in Chinese)
[10]Zhang Daoqiang,Chen Songcan,Zhou Zhihua.Twodimensional non-negative matrix factorization for face representation and recognition[J].Analysis and Modelling of Faces and Gestures,2005,3723:350-363.
[11]Gu Quanquan,Zhou Jie.Two dimensional nonnegative matrix factorization[C]∥16th IEEE International Conference on Image Processing.Cairo,Egypt:IEEE,2009:2069-2072.
[12]高宏娟.基于NMF改进算法的人脸识别仿真研究[J].计算机仿真,2011,28(12):231-235,303.Gao Hongjuan.Research and simulation of face recognition based on nmf and its improvements[J].Computer Simulation,2011,28(12):231-235,303.(in Chinese)
[13]张焱,汤宝平,刘自然,等.时频表示特征约简的旋转机械故障特征提取方法[J].振动工程学报,2015,28(1):156-163.Zhang Yan,Tang Baoping,Liu Ziran,et al.Rotating machine fault feature extraction based on reduced time frequency representation[J].Journal of Vibration Engineering,2015,28(1):156-163.(in Chinese)
[14]李兵,米双山,刘鹏远,等.二维非负矩阵分解在齿轮故障诊断中的应用[J].振动、测试与诊断,2012,32(5):836-840.Li Bing,Mi Shuangshan,Liu Pengyuan,et al.Application of two-dimensional non-negative matrix factorization for gear fault diagnosis[J].Journal of Vibration,Measurement&Diagnosis,2012,32(5):836-840.(in Chinese)
[15]Mallat S,Zhang Zhifeng.Matching pursuits with time-frequency dictionaries[J].IEEE Transactions on Signal Processing,1993,41(12):3397-3415.
[16]Lee D D,Seung H S.Learning the parts of objects by non-negative matrix factorization[J].Nature,1999,401(21):788-791.