Applying Bayesian Optimization of Parameters of Tunable Quality-Factor Wavelet Transform to Bearing Fault
-
摘要: 针对可调品质因子小波变换( Tunable Q-factor wavelet trans-form，TQWT)采用网格搜索和优化算法调参存在评估计算代价高的问题，提出基于贝叶斯优化TQWT参数的故障诊断算法。通过贝叶斯优化算法在TQWT参数空间内求取熵-峭综合目标函数最优解，据此设置TQWT参数分解轴承故障信号，选择熵-峭指标最小值对应子带信号，经TQWT逆变换后进行包络解调分析，最终由重构信号包络谱判别轴承故障类型。仿真实验和实测轴承信号分析表明，该算法可以准确提取轴承故障特征频率信息，实现早期故障诊断。Abstract: It is costly to use the grid search and optimization algorithm to tune the parameters of tunable quality-factor wavelet transform (TQWT). A method for bearing fault diagnosis based on the Bayesian optimization of TQWT parameters was proposed. The optimal solution of the entropy-kurtosis synthetic objective function was solved by using the Bayesian optimization algorithm in the space of TQWT parameters, according to which the TQWT parameters were set to decompose the original bearing fault signals. The sub-band signal with the minimum value of the entropy-kurtosis index was selected to reconstruct its feature signals with the inverse TQWT transform, and the signal was then processed with an envelope demodulation algorithm. The type of bearing fault was judged with the reconstructed feature signal envelope spectrum. The simulation results on the actually measured bearing vibration signals and their analysis show that the proposed method can accurately extract the characteristic frequency information on fault and diagnose bearing faults at an early stage.
-
Key words:
- bayesian optimization /
- TQWT /
- entropy-kurtosis index /
- fault diagnosis
-
图 6 提取故障特征时域波形与原冲击特征对比
Figure 6. Comparison of extracted fault characteristic time domain waveform with original impact characteristics
图 7 提取故障特征Hilbert包络谱（f=20 Hz）
Figure 7. Extracting Hilbert envelope spectrum of fault characteristics (f=20 Hz)
图 9 目标函数变化过程
Figure 9. Objective function variation process of inner ring fault signals
图 10 最显著特征子带选择结果
Figure 10. The most significant feature subband selection results of inner ring fault signals
图 13 1号轴承振动信号均方根值变化趋势
Figure 13. Root mean square (RMS) value variation trend of vibration signals of bearing 1
图 14 目标函数变化过程
Figure 14. Objective function variation process of outer ring fault signals
图 15 最显著特征子带选择结果
Figure 15. The most significant feature subband selection results of outer ring fault signals
图 16 故障特征提取结果（f = 235 Hz）
Figure 16. Fault feature extraction results of outer ring (f = 235 Hz)
图 17 以平均香农熵为目标函数提取故障特征
Figure 17. Utilizing average Shannon entropy as objective function for fault feature extraction
-
[1] SELESNICK I W. Wavelet transform with tunable Q-factor[J]. IEEE Transactions on Signal Processing, 2011, 59(8): 3560-3575. doi: 10.1109/TSP.2011.2143711 [2] 孔运, 王天杨, 褚福磊. 自适应TQWT滤波器算法及其在冲击特征提取中的应用[J]. 振动与冲击, 2019, 38(11): 9-16.KONG Y, WANG T Y, CHU F L. Adaptive TQWT filter algorithm and its application in impact feature extraction[J]. Journal of Vibration and Shock, 2019, 38(11): 9-16. (in Chinese) [3] 贺王鹏, 訾艳阳, 陈彬强, 等. 周期稀疏导向超小波在风力发电设备发电机轴承故障诊断中的应用[J]. 机械工程学报, 2016, 52(3): 41-48. doi: 10.3901/JME.2016.03.041HE W P, ZI Y Y, CHEN B Q, et al. Periodic sparsity oriented super-wavelet analysis with application to motor bearing fault detection of wind turbine[J]. Journal of Mechanical Engineering, 2016, 52(3): 41-48. (in Chinese) doi: 10.3901/JME.2016.03.041 [4] 任学平, 黄慧杰, 王朝阁, 等. 改进的TQWT在滚动轴承早期故障诊断的应用[J]. 振动、测试与诊断, 2020, 40(2): 317-325.REN X P, HUANG H J, WANG C G, et al. Application of improved TQWT in early fault diagnosis of rolling bearing[J]. Journal of Vibration, Measurement & Diagnosis, 2020, 40(2): 317-325. (in Chinese) [5] 唐贵基, 王晓龙. 参数优化变分模态分解方法在滚动轴承早期故障诊断中的应用[J]. 西安交通大学学报, 2015, 49(5): 73-81.TANG G J, WANG X L. Parameter optimized variational mode decomposition method with application to incipient fault diagnosis of rolling bearing[J]. Journal of Xi′an Jiaotong University, 2015, 49(5): 73-81. (in Chinese) [6] 刘嘉敏, 彭玲, 刘军委, 等. 遗传算法VMD参数优化与小波阈值轴承振动信号去噪分析[J]. 机械科学与技术, 2017, 36(11): 1695-1700.LIU J M, PENG L, LIU J W, et al. Denoising analysis of bearing vibration signal based on genetic algorithm and wavelet threshold VMD[J]. Mechanical Science and Technology for Aerospace Engineering, 2017, 36(11): 1695-1700. (in Chinese) [7] 王振亚, 姚立纲, 戚晓利, 等. 参数优化变分模态分解与多域流形学习的行星齿轮箱故障诊断[J]. 振动与冲击, 2021, 40(1): 110-118.WANG Z Y, YAO L G, QI X L, et al. Fault diagnosis of planetary gearbox based on parameter optimized VMD and multi-domain manifold learning[J]. Journal of Vibration and Shock, 2021, 40(1): 110-118. (in Chinese) [8] SHAHRIARI B, SWERSKY K, WANG Z Y, et al. Taking the human out of the loop: A review of Bayesian optimization[J]. Proceedings of the IEEE, 2016, 104(1): 148-175. doi: 10.1109/JPROC.2015.2494218 [9] 崔佳旭, 杨博. 贝叶斯优化方法和应用综述[J]. 软件学报, 2018, 29(10): 3068-3090.CUI J X, YANG B. Survey on Bayesian optimization methodology and applications[J]. Journal of Software, 2018, 29(10): 3068-3090. (in Chinese) [10] 任婷玉, 梁中耀, 刘永, 等. 基于贝叶斯优化的三维水动力-水质模型参数估值方法[J]. 环境科学学报, 2019, 39(6): 2024-2032.REN T Y, LIANG Z Y, LIU Y, et al. The parameters estimation method based on Bayesian optimization for complex water quality models[J]. Acta Scientiae Circumstantiae, 2019, 39(6): 2024-2032. (in Chinese) [11] 常淼, 沈艳霞. 基于贝叶斯优化CNN的风电轴承故障诊断策略[J]. 噪声与振动控制, 2021, 41(6): 77-83.CHANG M, SHEN Y X. Fault diagnosis strategy of wind turbine bearings based on Bayesian optimized CNN[J]. Noise and Vibration Control, 2021, 41(6): 77-83. (in Chinese) [12] 石怀涛, 尚亚俊, 白晓天, 等. 基于贝叶斯优化的SWDAE-LSTM滚动轴承早期故障预测方法研究[J]. 振动与冲击, 2021, 40(18): 286-297.SHI H T, SHANG Y J, BAI X T, et al. Early fault prediction method combining SWDAE and LSTM for rolling bearings based on Bayesian optimization[J]. Journal of Vibration and Shock, 2021, 40(18): 286-297. (in Chinese) [13] MOCKUS J. Bayesian approach to global optimization: theory and applications[M]. Dordrecht: Springer, 1989. [14] 张龙, 易剑昱, 熊国良, 等. MED与TQWT相结合的滚动轴承早期故障特征提取[J]. 机械科学与技术, 2021, 40(6): 863-869.ZHANG L, YI J Y, XIONG G L, et al. Incipient fault feature extraction for rolling bearings combined with MED and TQWT[J]. Mechanical Science and Technology for Aerospace Engineering, 2021, 40(6): 863-869. (in Chinese) [15] 张龙, 毛志德, 杨世锡, 等. 基于包络谱带通峭度的改进谱峭度方法及在轴承诊断中的应用[J]. 振动与冲击, 2018, 37(23): 171-179.ZHANG L, MAO Z D, YANG S X, et al. An improved Kurtogram based on band-pass envelope spectral Kurtosis with its application in bearing fault diagnosis[J]. Journal of Vibration and Shock, 2018, 37(23): 171-179. (in Chinese) [16] 何勇, 王红, 谷穗. 一种基于遗传算法的VMD参数优化轴承故障诊断新方法[J]. 振动与冲击, 2021, 40(6): 184-189.HE Y, WANG H, GU S. New fault diagnosis approach for bearings based on parameter optimized VMD and genetic algorithm[J]. Journal of Vibration and Shock, 2021, 40(6): 184-189. (in Chinese) [17] 项巍巍, 蔡改改, 樊薇, 等. 基于双调Q小波变换的瞬态成分提取及轴承故障诊断应用研究[J]. 振动与冲击, 2015, 34(10): 34-39.XIANG W W, CAI G G, FAN W, et al. Transient feature extraction based on double-TQWT and its application in bearing fault diagnosis[J]. Journal of Vibration and Shock, 2015, 34(10): 34-39. (in Chinese) -
下载:
点击查看大图
计量
- 文章访问数: 40
- HTML全文浏览量: 15
- PDF下载量: 0
- 被引次数: 0
