基于能量分布的自适应超小波变换在轴承故障诊断中的应用

PDF(2829 KB)

振动与冲击 ›› 2025, Vol. 44 ›› Issue (15) : 224-234.

故障诊断分析

基于能量分布的自适应超小波变换在轴承故障诊断中的应用

侯俊琪，肖松华，孙蓓蓓*

作者信息 +

Application of energy distribution-based adaptive superlet transform in bearing fault diagnosis

HOU Junqi, XIAO Songhua, SUN Beibei*

Author information +

文章历史 +

摘要

超小波变换（Superlet Transform，SLT）是一种新的高分辨率时频分析方法，在能量聚集度、噪声鲁棒性等方面明显优于短时傅里叶变换、连续小波变换等经典时频分析方法。然而，由于故障轴承振动信号中的异常频率成分分布广泛而稀疏，对其进行SLT时会出现计算量过大的问题。为提升SLT计算效率，提出基于能量分布的自适应超小波变换（Energy Distribution based Adaptive Superlet Transform，ED-ASLT）方法。首先，利用Welch法进行功率谱估计，获得信号频带能量分布；随后，基于能量分布，进行频率非等间距自适应采样，得到一系列超小波中心频率；继而，根据中心频率值高低和中心频率处能量高低，确定超小波中的小波数量和窗长，构造超小波；最后，利用构造的超小波，对信号进行超小波变换。ED-ASLT方法能够根据具体故障信号的频带能量分布，识别信号中可能反映故障信息的关键频段，自适应地确定超小波参数，对信号进行高能量聚集度、高噪声鲁棒性、高效的时频分析，有助于对信号中的异常成分进行更精确的时频定位，抵御噪声的干扰，提高故障诊断准确率和效率。分别利用帕德博恩大学和东南大学实验室的轴承振动信号，从能量聚集度、噪声鲁棒性、计算耗时等方面将ED-ASLT方法与多种常用时频分析方法进行对比。结果表明，ED-ASLT在保持超小波变换高能量聚集度、高噪声鲁棒性优势的同时，能够大幅减少计算耗时，有助于为故障诊断提供更优质的判断依据。

Abstract

The Superlet Transform (SLT), which is a novel high-resolution time-frequency analysis method, is obviously superior to classical time-frequency analysis methods such as the Short-time Fourier Transform and the Continuous Wavelet Transform in terms of energy aggregation and noise robustness. However, when applying SLT to bearing vibration signals with widely distributed and sparse frequency components, meeting diagnosis requirements in practical becomes challenging. To enhance computational efficiency, Energy Distribution based Adaptive SLT (ED-ASLT) is proposed. Firstly, the frequency energy distribution of signal is obtained based on Welch method. Then, the superlets center frequencies adaptive sampling is carried out based on the energy distribution. Then, the window lengths of wavelets in each superlet are determined according to the center frequency value and the energy at the center frequency. Finally, the superlets are constructed to complete the time-frequency analysis. The ED-ASLT method can identify the key frequency bands that may reflect fault information in the signal according to the energy distribution of the specific fault signal, determine the SLT parameters adaptively, and perform high energy aggregation, high noise robustness and efficient time-frequency analysis of the signal, which is helpful for more accurate time-frequency positioning of the abnormal components in the signal and resist the interference of noise. Improve the accuracy and efficiency of fault diagnosis. The ED-ASLT method were compared with other time-frequency analysis methods in terms of energy aggregation, noise robustness and time cost by using bearing vibration signals from laboratories of Paderborn University and Southeast University. It is verified that the proposed method can greatly reduce the time cost while maintaining the advantages of high energy aggregation and high noise robustness of SLT, which is helpful to provide higher-quality criteria for fault diagnosis.

导出引用

侯俊琪, 肖松华, 孙蓓蓓. 基于能量分布的自适应超小波变换在轴承故障诊断中的应用[J]. 振动与冲击, 2025, 44(15): 224-234

HOU Junqi, XIAO Songhua, SUN Beibei. Application of energy distribution-based adaptive superlet transform in bearing fault diagnosis[J]. Journal of Vibration and Shock, 2025, 44(15): 224-234

参考文献

[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(01): 63-72.
WANG Guobiao, HE Zhengjia, CHEN Xuefeng, et al. Basic Research on Machinery Fault Diagnosis—What is the Prescription[J]. Journal of Mechanical Engineering, 2013, 49(01): 63-72.
[2] Yaguo Lei, Bin Yang, Xinwei Jiang, et al. Applications of machine learning to machine fault diagnosis: A review and roadmap[J]. Mechanical Systems and Signal Processing, 2020, 138: 06587.
[3] 樊翔翔, 项载毓, 孙瑞雪, 等. 基于小波时频分析和Inception-BiGRU模型的盾构滚刀偏磨故障诊断[J]. 振动与冲击, 2023, 42(15): 232-240.
FAN Xiangxiang, XIANG Zailiu, SUN Ruixue, et al. Fault diagnosis of TBM hob eccentric wear based on wavelet time-frequency analysis and Inception-BiGRU model[J]. Journal of vibration and shock, 2023, 42(15): 232-240.
[4] 陈起磊, 蒋亦悦, 唐瑶, 等. 基于时频图与改进图卷积神经网络的异步电机故障诊断方法[J]. 振动与冲击, 2022, 41(24): 241-248.
CHEN Qilei, JIANG Yiyue, TANG Yao, et al. An induction motor fault diagnosis method based on the time-frequency image method and an improved graph convolutional network[J]. Journal of vibration and shock, 2022, 41(24): 241-248.
[5] Tang X, Xu Z, Wang Z. A Novel Fault Diagnosis Method of Rolling Bearing Based on Integrated Vision Transformer Model[J]. Sensors, 2022, 22(10): 3878.
[6] Xu Z, Tang X, Wang Z. A Multi-Information Fusion ViT Model and Its Application to the Fault Diagnosis of Bearing with Small Data Samples[J]. Machines. 2023, 11(2):277.
[7] Chong Chen, Chao Liu, Tao Wang, et al. Compound fault diagnosis for industrial robots based on dual-transformer networks[J], Journal of Manufacturing Systems, 2023, 66: 163-178.
[8] Yu X, Wang S, Xu H, et al. Intelligent fault diagnosis of rotating machinery under variable working conditions based on deep transfer learning with fusion of local and global time–frequency features[J]. Structural Health Monitoring, 2024, 23(4): 2238-2254.
[9] Jie Liu, Changhe Zhang, Xingxing Jiang. Imbalanced fault diagnosis of rolling bearing using improved MsR-GAN and feature enhancement-driven CapsNet[J]. Mechanical Systems and Signal Processing, 2022, 168: 108664.
[10] X. Yu, Y. Wang, Z. Liang, et al. An Adaptive Domain Adaptation Method for Rolling Bearings’ Fault Diagnosis Fusing Deep Convolution and Self-Attention Networks[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 3509814.
[11] Liang Meng, Yuanhao Su, Xiaojia Kong, et al. Intelligent fault diagnosis of gearbox based on differential continuous wavelet transform-parallel multi-block fusion residual network[J]. Measurement, 2023, 206: 112318.
[12] HLAWATSCH F, BOUDREAUX-BARTELS G F. Linear and quadratic time-frequency signal representations[J]. IEEE Signal Processing Magazine, 1992,9(2): 21-67.
[13] Moca Vasile V., Barzan H., Nagy-Dabacan A., et al. Time-frequency super-resolution with superlets[J]. Nature Communications, 2021, 12(1): 337.
[14] P. M. Tripathi, A. Kumar, M. Kumar, et al. Multilevel Classification and Detection of Cardiac Arrhythmias With High-Resolution Superlet Transform and Deep Convolution Neural Network[J] IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-13.
[15] S. Singhal, M. Kumar. GSMD-SRST: Group Sparse Mode Decomposition and Superlet-Transform-Based Technique for Multilevel Classification of Cardiac Arrhythmia[J]. IEEE Sensors Journal,2024, 24(6): 8160-8169.
[16] Pankaj, A. Kumar, M. Kumar, et al. Edge-Based Computation of Super-Resolution Superlet Spectrograms for Real-Time Estimation of Heart Rate Using an IoMT-Based Reference-Signal-Less PPG Sensor[J]. IEEE Internet of Things Journal, 2024, 11(5): 8647-8657.
[17] Pankaj, Ashish Kumar, Rama Komaragiri, et al. A novel CS-NET architecture based on the unification of CNN, SVM and super-resolution spectrogram to monitor and classify blood pressure using photoplethysmography[J]. Computer Methods and Programs in Biomedicine, 2023, 240: 107716.
[18] Pankaj, A. Kumar, M. Kumar, et al. STSR: Spectro-Temporal Super-Resolution Analysis of a Reference Signal Less Photoplethysmogram for Heart Rate Estimation During Physical Activity[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-10.
[19] C. Orihuela, E. Lujan, S. Merino, et al. Adaptive Superlet-Based Shear Wave Speed Estimation for Crawling Wave Sonoelastography[C]// 2024 IEEE UFFC Latin America Ultrasonics Symposium (LAUS), Montevideo, Uruguay, 2024, 1-4.
[20] Tho N.H.T. Tran, Lawrence H. Le, Boyi Li, et al. Visualization of ultrasonic-guided-wave propagation behaviors in human long bone[J]. Biomedical Signal Processing and Control, 2024, 95(Part A): 106335.
[21] Liang, X., Wang, R., Wu, H., et al. A Novel Time-Frequency Parameterization Method for Oscillations in Specific Frequency Bands and Its Application on OPM-MEG[J]. Bioengineering, 2024, 11: 773.
[22] D. B. Mureșan, R. -D. Ciure, E. R. Ardelean, et al. Spike sorting using Superlets: Evaluation of a novel feature space for the discrimination of neuronal spikes[C]// 2022 IEEE 18th International Conference on Intelligent Computer Communication and Processing (ICCP), Cluj-Napoca, Romania, 2022: 229-235.
[23] L. Mignone, C. Ilioudis, C. Clemente, et al. Enhancing Micro-Doppler Classification Using Superlet-Based Time-Frequency Distribution[J]. IEEE Transactions on Aerospace and Electronic Systems, 2023, 59(6): 9831-9838.
[24] Kavita Bhatt, N. Jayanthi, Manjeet Kumar. High-resolution superlet transform based techniques for Parkinson's disease detection using speech signal[J]. Applied Acoustics, 2023, 214: 109657.
[25] Y. Tian, J. Gao, D. Wang, et al. Super-Resolution Optimal Basic Wavelet Transform and Its Application in Thin-Bed Thickness Characterization[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-12.
[26] Hongchun Sun, Xu Cao, Changdong Wang, et al. An interpretable anti-noise network for rolling bearing fault diagnosis based on FSWT[J]. Measurement, 2022, 190: 110698.
[27] Xiaoan Yan, Wang-Ji Yan, Yadong Xu, et al. Machinery multi-sensor fault diagnosis based on adaptive multivariate feature mode decomposition and multi-attention fusion residual convolutional neural network[J]. Mechanical Systems and Signal Processing, 2023, 202: 110664.
[28] Changdong Wang, Jingli Yang, Huamin Jie, et al. An uncertainty perception metric network for machinery fault diagnosis under limited noisy source domain and scarce noisy unknown domain[J]. Advanced Engineering Informatics, 2024, 62: 102682.
[29] Changdong Wang, Bowen Tian, Jingli Yang, et al. Neural -transformer: A brain-inspired lightweight mechanical fault diagnosis method under noise[J].Reliability Engineering & System Safety, 2024, 251: 110409.
[30] S. Mitra, C. Koley. Early and Intelligent Bearing Fault Detection Using Adaptive Superlets[J]. IEEE Sensors Journal, 2023, 23(7): 7992-8000.
[31] Cancan Yi, Jun Liu, Zhaohong Yu, et al. High-order Synchrosqueezing Superlets Transform and its application to mechanical fault diagnosis[J]. Applied Acoustics, 2023, 204: 109226.
[32] Peng Zhou, Shiqian Chen, Qingbo He, et al. Rotating machinery fault-induced vibration signal modulation effects: A review with mechanisms, extraction methods and applications for diagnosis[J]. Mechanical Systems and Signal Processing, 2023, 200: 110489.
[33] Kaľavský A, Niesłony A, Huňady R. Influence of PSD Estimation Parameters on Fatigue Life Prediction in Spectral Method[J]. Materials, 2023, 16(3):1007.
[34] 袁静,姚泽,胡雯玥,等.滚动轴承复合故障的时频能量聚集谱诊断方法[J].振动与冲击, 2023, 42(02): 285-292+320.
YUAN Jing, YAO Ze, HU Wenyue, et al. Time-frequency energy aggregation spectrum diagnosis method for compound faults of rolling bearings[J]. Journal of Vibration and Shock, 2023, 42(02): 285-292+320.
[35] 李亦佳,王静,王正方,等.基于多重同步压缩变换的微震信号去噪方法研究[J].应用基础与工程科学学报, 2022,30(02):486-500.
LI Yijia, WANG Jing, WANG Zhengfang, et al. Research on De-noising Method of Microseismic Signal Based on Multi-Synchronous Compression Transform[J]. Journal of Basic Science and Engineering, 2022,30(02):486-500.