Time-varying Noise Structure Inspired Adaptive Weighted Sparse Model for Aero-engine Bearing Fault Diagnosis

doi:10.3901/JME.2023.17.162

Abstract

Abstract: Due to non-stationary operating conditions and time-varying air flows, the background noises embedded into aero-engine vibration signals have time-varying structures or different statistical variances in different temporal parts. Meanwhile, the fault waveforms of aero-engine bearing present an overlapping distortion morphology. Therefore, it is a challenging task to extract the latent and distorted fault patterns for popular fault diagnosis methods. Exploring the time-varying statistical variance structures, an adaptive weighted sparse diagnosis model is proposed. Based on the characteristic period of the fault signal, a segmentation operator is firstly designed to construct two-dimensional matrix with low-rank patterns, and then an singular value decomposition(SVD) Dictionary is established adaptively to obtain the sparse representation of overlapping distortion fault waveforms. Secondly, the time-varying variance structure of background noises is revealed by sufficient statistical analysis, and then a weighted matrix with different column values is designed to describe that time-varying priors. Furthermore, the low-rank patterns of data matrix are incorporated into the weighted matrix through designating different weights to all rows based on the singular values. Based on the sparse representing model and elaborated weighted-matrix, an adaptive weighted sparse diagnosis model(AWSM) is constructed and meanwhile an optimization algorithm is developed for it. Simulation analysis shows that the proposed algorithm can effectively filter out the time-varying noise of aero-engine bearings, and reliably extract the weak fault features of bearings. Finally, experiments indicate that the proposed algorithm can perform the fault diagnosis of aero-engine bearing with spalling area of 1.0 mm² at speed up to 25 000 r/min.

Key words: aero-engine bearing, fault diagnosis, time-varying gaussian noise, sparse representation, adaptive weighted matrix

CLC Number:

TH133
TP206

ZHANG Han, TIAN Yi, DU Zhaohui. Time-varying Noise Structure Inspired Adaptive Weighted Sparse Model for Aero-engine Bearing Fault Diagnosis[J]. Journal of Mechanical Engineering, 2023, 59(17): 162-174.

References

[1] 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,2015,51(1):97-105. ZHANG Han,DU Zhaohui,FANG Zuowei,et al. Sparse decomposition based aero-engine's bearing fault diagnosis[J]. Journal of Mechanical Engineering,2015,51(1):97-105.
[2] 陈光,洪杰,马艳红. 航空燃气涡轮发动机结构[M]. 北京:北京航空航天大学出版社,2010. CHEN Guang,HONG Jie,MA Yanhong. Structure of aviation gas turbine engine[M]. Beijing:Beijing University of Aeronautics and Astronautics Press,2010.
[3] 刘朋,王黎钦,张传伟,等. 航空发动机主轴轴承状态监测研究现状与发展趋势[J]. 航空动力学报,2022,37(02):330-343. LIU Peng,WANG Liqin,ZHANG Chuanwei,et al. Research status and development trend of condition monitoring on main-shaft bearings used in aircraft engines[J]. Journal of Aerospace Power,2022,37(2):330-343.
[4] 张晗,王兴,田毅,等. 稀疏低秩协同正则优化及航空轴承故障诊断[J]. 西安交通大学学报,2021,55(11):46-58. ZHANG Han,WANG Xing,TIAN Yi,et al. Collaborative sparse low rank regularization for aero-engine bearing fault diagnosis[J]. Journal of Xi'an Jiaotong University,2021,55(11):46-58.
[5] QIN Yi,LI Chengcheng,CAO Folin,et al. A fault dynamic model of high-speed angular contact ball bearings[J]. Mechanism and Machine Theory,2020,143:103627.
[6] WANG Xiaoxian,LU Siliang,CHEN Kang,et al. Bearing fault diagnosis of switched reluctance motor in electric vehicle powertrain via multisensor data fusion[J]. IEEE Transactions on Industrial Informatics,2022,18(4):2452-2464.
[7] WANG Shibin,CHEN Xuefeng,SELESNICK I W,et al. Matching synchrosqueezing transform:a useful tool for characterizing signals with fast varying instantaneous frequency and application to machine fault diagnosis[J]. Mechanical Systems and Signal Processing,2018,100:242-288.
[8] XIAO Maohua,ZHANG Wei,WEN Kai,et al. Fault diagnosis based on BP neural network optimized by beetle algorithm[J]. Chinese Journal of Mechanical Engineering,2021,34(1):1-10.
[9] GUO Jianchun,SI Zetian,XIANG Jiawei. A compound fault diagnosis method of rolling bearing based on wavelet scattering transform and improved soft threshold denoising algorithm[J]. Measurement,2022,196:111276.
[10] 郭莹莹,赵学智,上官文斌,等. 柔性椭圆轴承故障频率分析与CMWT-FH特征提取[J]. 机械工程学报,2019,55(23):154-161. GUO Yingying,ZHAO Xuezhi,SHANGGUAN Wenbin,et al. Fault frequency analysis and feature extraction based on CMWT-FH of elliptically shaped bearing[J]. Journal of Mechanical Engineering,2019,55(23):154-161.
[11] ZHANG Shuo,LIU Zhiwen,HE Sihai,et al. Improved double TQWT sparse representation using the MQGA algorithm and new norm for aviation bearing compound fault detection[J]. Engineering Applications of Artificial Intelligence,2022,110:104741.
[12] HU Yongtao,THANG Shuqing,JIANG Anqi,et al. A new method of wind turbine bearing fault diagnosis based on multi-masking empirical mode decomposition and fuzzy C-means clustering[J]. Chinese Journal of Mechanical Engineering,2019,32(1):1-12.
[13] SUN Yongjian,LI Shaohui,WANG Yaling,et al. Fault diagnosis of rolling bearing based on empirical mode decomposition and improved manhattan distance in symmetrized dot pattern image[J]. Mechanical Systems and Signal Processing,2021,159:107817.
[14] 彭丹丹,刘志亮,靳亚强,等. 基于软筛分停止准则的改进经验模态分解及其在旋转机械故障诊断中的应用[J]. 机械工程学报,2019,55(10):122-132. PENG Dandan,LIU Zhiliang,JIN Yaqiang,et al. Improved EMD with a soft sifting stopping criterion and its application to fault diagnosis of rotating machinery[J]. Journal of Mechanical Engineering,2019,55(10):122-132.
[15] HU Yue,BAO Wenjie,TU Xiaotong,et al. An Adaptive spectral kurtosis method and its application to fault detection of rolling element bearings[J]. IEEE Transactions on Instrumentation and Measurement,2020,69(3):739-750.
[16] YANG D M. The detection of motor bearing fault with maximal overlap discrete wavelet packet transform and teager energy adaptive spectral kurtosis[J]. Sensors (Basel),2021,21(20):6895.
[17] LIANG Kaixuan,ZHAO Ming,LIN Jing,et al. Maximum average kurtosis deconvolution and its application for the impulsive fault feature enhancement of rotating machinery[J]. Mechanical Systems and Signal Processing,2021,149:107323.
[18] WANG Zhijian,ZHOU Jie,DU Wenhua,et al. Bearing fault diagnosis method based on adaptive maximum cyclostationarity blind deconvolution[J]. Mechanical Systems and Signal Processing,2022,162:108018.
[19] 李政,张炜,明安波,等. 基于IEWT和MCKD的滚动轴承故障诊断方法[J]. 机械工程学报,2019,55(23):136-146. LI Zheng,ZHANG Wei,MING Anbo,et al. A novel fault diagnosis method based on improved empirical wavelet transform and maximum correlated kurtosis deconvolution for rolling element bearing[J]. Journal of Mechanical Engineering,2019,55(23):136-146.
[20] ZHANG Han,CHEN Xuefeng,DU Zhaohui,et al. Nonlocal sparse model with adaptive structural clustering for feature extraction of aero-engine bearings[J]. Journal of Sound and Vibration,2016,368:223-248.
[21] ZHAO Zhibin,WU Shuming,QIAO Baijie,et al. Enhanced sparse period-group lasso for bearing fault diagnosis[J]. IEEE Transactions on Industrial Electronics,2019,66(3):2143-2153.
[22] ZHAO Zhibin,QIAO Baijie,WANG Shibin,et al. A weighted multi-scale dictionary learning model and its applications on bearing fault diagnosis[J]. Journal of Sound and Vibration,2019,446:429-452.
[23] STIEF A,OTTEWILL J R,BARANOWSKI J,et al. A PCA and two-stage bayesian sensor fusion approach for diagnosing electrical and mechanical faults in induction motors[J]. IEEE Transactions on Industrial Electronics,2019,66(12):9510-9520.
[24] ZHU Jing,HU Tianzhen,JIANG Bin,et al. Intelligent bearing fault diagnosis using PCA-DBN framework[J]. Neural Computing & Applications,2020,32(14):10773-10781.
[25] QIN Yi,ZOU Jingqiang,TANG Baoping,et al. Transient feature extraction by the improved orthogonal matching pursuit and K-SVD algorithm with adaptive transient dictionary[J]. IEEE Transactions on Industrial Informatics,2020,16(1):215-227.
[26] ZENG Ming,CHEN Zhen. SOSO boosting of the K-SVD denoising algorithm for enhancing fault-induced impulse responses of rolling element bearings[J]. IEEE Transactions on Industrial Electronics,2020,67(2):1282-1292.
[27] DU Zhaohui,CHEN Xuefeng,ZHANG Han,et al. Weighted low-rank sparse model via nuclear norm minimization for bearing fault detection[J]. Journal of Sound and Vibration,2017,400:270-287.
[28] ZHANG Han,CHEN Xuefeng,ZHANG Xiaoli,et al. Aero-engine bearing fault detection:a clustering low-rank approach[J]. Mechanical Systems and Signal Processing,2020,138:106529.
[29] XU Jun,ZHANG Lei,ZHANG David. A trilateral weighted sparse coding scheme for real-world image denoising[C]//Proceedings of the 15th European Conference on Computer Vision,September 8-14,Munich,GERMANY. Proceedings:Lecture Notes in Computer Science,2018:20-36.
[30] DONOHO D L. De-noising by soft-thresholding[J]. IEEE Transactions on Information Theory,1995,41(3):613-627.
[31] COMBETTES P L,PESQUET J C. Proximal splitting methods in signal processing[J]. Fixed-point Algorithms for Inverse Problems in Science and Engineering,Springer. 2011:185-212.
[32] ANTONI J. Fast computation of the kurtogram for the detection of transient faults[J]. Mechanical Systems and Signal Processing,2007,21(1):108-124.