Rolling bearing fault diagnosis method based on grey wolf algorithm optimized feature mode decomposition
-
摘要:
针对滚动轴承微弱故障特征提取难的问题，提出一种基于灰狼算法优化特征模态分解的滚动轴承故障诊断方法。首先通过特征模态分解对信号进行分解，获得若干模态分量；然后采用峭度-相关系数筛选准则对模态分量筛选分类，输出高噪信号和低噪信号；其次对高噪信号进行小波包分解，以峭度、偏度和信息熵组成的融合指标对信号分量进行加权重构，完成信号降噪和故障特征增强；同时为了解决特征模态分解的关键参数和小波包变换的小波包基需要人为设置的弊端，选取重构信号的信息熵除以峭度为目标函数，使用灰狼算法在一定范围内进行寻优并代入；最后对信号进行包络解调，提取故障特征。采用仿真信号、西储大学数据集、涡扇发动机主轴承实验台数据和深沟球轴承故障实验数据对所提方法进行验证。结果表明处理后的信号故障特征明显，方法降噪效果良好，仿真加噪信号的信噪比提高了10.76，航空主轴承加噪信号的峭度值提高了1.94。
Abstract:Aiming at the problem that the vibration signal fault features of rolling bearing are weak when the fault occurs, a rolling bearing fault diagnosis method based on grey wolf algorithm optimized feature mode decomposition was proposed. Firstly, the signal was decomposed by feature mode decomposition to obtain several modal components. Then, the kurtosis-correlation coefficient selection criterion was used to filter and classify the modal components, and the high noise signal and low noise signal were output. Secondly, the high noise signal was decomposed by wavelet packet, and the signal component was reconstructed by weighted fusion index composed of kurtosis, skewness and information entropy to complete signal noise reduction and fault feature enhancement. At the same time, in order to solve the disadvantage that the key parameters of feature mode decomposition and the wavelet packet basis of wavelet packet transform need to be set artificially, the information entropy of the reconstructed signal divided by the kurtosis was selected as the objective function, and the grey wolf algorithm was used to optimize in a certain range and substituted. Finally, the signal was envelope demodulated to extract fault features. The simulation signals, the data set of Western Reserve University, the data of the main bearing test bed of turbofan engine and the fault test data of deep groove ball bearing were used to verify the proposed method. The results showed that the fault features of the processed signal were obvious, and the noise reduction effect of the method was good, the signal-to-noise ratio of the simulated noisy signal increased by 10.76, and the kurtosis value of the aircraft main bearing noisy signal increased by 1.94.
-
图 18 主轴承外圈故障信号包络谱
Figure 18. Envelope spectrum of main bearing outer ring fault signal
图 37 深沟球轴承重构信号包络谱
Figure 37. Reconstructed signal envelope spectrum of deep groove bearing
表 2 主轴承几何参数
Table 2. Main bearing parameters
参数 数值 轴承节径 Dm/mm 167.5375 滚动体直径 dr/mm 22.225 滚动体数量 Z 20 滚动体接触角$ {\alpha }_{{\mathrm{o}}} $/（°） 32～48 
下载: 导出CSV
表 3 信号峭度值
Table 3. Kurtosis value
信号 峭度值 原始信号 3.04 高噪信号 2.32 重构信号 4.26 重构信号（随机参数） 3.43 重构信号（WPD） 3.54
下载: 导出CSV
表 4 深沟球轴承几何参数
Table 4. Deep groove parameters
参数 数值 轴承节径 Dm/mm 39.04 滚动体直径 dr/mm 7.94 滚动体数量 Z 9 滚动体接触角 $ \alpha_{\mathrm{o}} $/（°） 0
下载: 导出CSV
表 5 峭度值变化
Table 5. Change of kurtosis value
信号 峭度值变化 原始信号 13.71 加噪信号 （2 dB） 2.99 加噪信号 （1 dB） 1.58 加噪信号 （−5 dB） 0.92
下载: 导出CSV
-
[1] 栾孝驰, 那万晓, 沙云东, 等. 基于特征量阈值判决的轴承故障诊断方法[J]. 推进技术, 2022, 43(4): 200921. LUAN Xiaochi, NA Wanxiao, SHA Yundong, et al. Bearing fault diagnosis method based on eigenvalue threshold decision[J]. Journal of Propulsion Technology, 2022, 43(4): 200921. (in Chinese doi: 10.13675/j.cnki.tjjs.200921LUAN Xiaochi, NA Wanxiao, SHA Yundong, et al. Bearing fault diagnosis method based on eigenvalue threshold decision[J]. Journal of Propulsion Technology, 2022, 43(4): 200921. (in Chinese) doi: 10.13675/j.cnki.tjjs.200921 [2] XU Fan, XIE Weida. A method combining refined composite multiscale fuzzy entropy with PSO-SVM for roller bearing fault diagnosis[J]. Journal of Central South University, 2019, 26(9): 2404-2417. doi: 10.1007/s11771-019-4183-7 [3] 陈鹏. 基于振动信号的滚动轴承故障诊断方法综述[J]. 轴承, 2022(6): 1-6. CHEN Peng. Review on fault diagnosis methods for rolling bearings based on vibration signals[J]. Bearing, 2022(6): 1-6. (in Chinese doi: 10.19533/j.issn1000-3762.2022.06.001CHEN Peng. Review on fault diagnosis methods for rolling bearings based on vibration signals[J]. Bearing, 2022(6): 1-6. (in Chinese) doi: 10.19533/j.issn1000-3762.2022.06.001 [4] 党建. 大型旋转机械振动信号分析与早期故障辨识方法研究[D]. 西安: 西安理工大学, 2018. DANG Jian. Research on methods of vibration signal processing and incipient fault identification for large rotating machine[D]. Xi’an: Xi’an University of Technology, 2018. (in ChineseDANG Jian. Research on methods of vibration signal processing and incipient fault identification for large rotating machine[D]. Xi’an: Xi’an University of Technology, 2018. (in Chinese) [5] 戴洪德, 陈强强, 戴邵武, 等. 基于平滑先验分析和排列熵的滚动轴承故障诊断[J]. 推进技术, 2020, 41(8): 1841-1849. DAI Hongde, CHEN Qiangqiang, DAI Shaowu, et al. Rolling bearing fault diagnosis based on smoothness priors approach and permutation entropy[J]. Journal of Propulsion Technology, 2020, 41(8): 1841-1849. (in Chinese doi: 10.13675/j.cnki.tjjs.190135DAI Hongde, CHEN Qiangqiang, DAI Shaowu, et al. Rolling bearing fault diagnosis based on smoothness priors approach and permutation entropy[J]. Journal of Propulsion Technology, 2020, 41(8): 1841-1849. (in Chinese) doi: 10.13675/j.cnki.tjjs.190135 [6] 赵俊豪, 栾孝驰, 沙云东. 加权特征参数信息重构方法及其在主轴承故障诊断中的应用[J]. 推进技术, 2025, 46(1): 2402027. ZHAO Junhao, LUAN Xiaochi, SHA Yundong. Weighted feature parameter information reconstruction method and its application in main bearing fault diagnosis[J]. Journal of Propulsion Technology, 2025, 46(1): 2402027. (in Chinese doi: 10.13675/j.cnki.tjjs.2402027ZHAO Junhao, LUAN Xiaochi, SHA Yundong. Weighted feature parameter information reconstruction method and its application in main bearing fault diagnosis[J]. Journal of Propulsion Technology, 2025, 46(1): 2402027. (in Chinese) doi: 10.13675/j.cnki.tjjs.2402027 [7] 栾孝驰, 沙云东, 柳贡民, 等. 基于WPD-KVI-Hilbert变换相结合的滚动轴承早期故障特征精准识别[J]. 推进技术, 2022, 43(2): 210408. LUAN Xiaochi, SHA Yundong, LIU Gongmin, et al. Accurate identification for early fault features of rolling bearings based on WPD-KVI-Hilbert transform[J]. Journal of Propulsion Technology, 2022, 43(2): 210408. (in Chinese doi: 10.13675/j.cnki.tjjs.210408LUAN Xiaochi, SHA Yundong, LIU Gongmin, et al. Accurate identification for early fault features of rolling bearings based on WPD-KVI-Hilbert transform[J]. Journal of Propulsion Technology, 2022, 43(2): 210408. (in Chinese) doi: 10.13675/j.cnki.tjjs.210408 [8] 刘新航, 栾孝驰, 赵俊豪, 等. 基于综合动态筛选的航空发动机滚动轴承故障特征提取方法[J]. 航空动力学报, 2025, 40(7): 20240210. LIU Xinhang, LUAN Xiaochi, ZHAO Junhao, et al. Aircraft engine rolling bearings based on comprehensive dynamic screening Fault feature extraction method[J]. Journal of Aerospace Power, 2025, 40(7): 20240210. (in Chinese doi: 10.13224/j.cnki.jasp.20240210LIU Xinhang, LUAN Xiaochi, ZHAO Junhao, et al. Aircraft engine rolling bearings based on comprehensive dynamic screening Fault feature extraction method[J]. Journal of Aerospace Power, 2025, 40(7): 20240210. (in Chinese) doi: 10.13224/j.cnki.jasp.20240210 [9] 向丹, 岑健. 基于EMD熵特征融合的滚动轴承故障诊断方法[J]. 航空动力学报, 2015, 30(5): 1149-1155. XIANG Dan, CEN Jian. Method of roller bearing fault diagnosis based on feature fusion of EMD entropy[J]. Journal of Aerospace Power, 2015, 30(5): 1149-1155. (in Chinese doi: 10.13224/j.cnki.jasp.2015.05.016XIANG Dan, CEN Jian. Method of roller bearing fault diagnosis based on feature fusion of EMD entropy[J]. Journal of Aerospace Power, 2015, 30(5): 1149-1155. (in Chinese) doi: 10.13224/j.cnki.jasp.2015.05.016 [10] 隋文涛, 张丹, WANG W. 基于EMD和MKD的滚动轴承故障诊断方法[J]. 振动与冲击, 2015, 34(9): 55-59, 64. SUI Wentao, ZHANG Dan, WANG W. Fault diagnosis of rolling element bearings based on EMD and MKD[J]. Journal of Vibration and Shock, 2015, 34(9): 55-59, 64. (in Chinese doi: 10.13465/j.cnki.jvs.2015.09.010SUI Wentao, ZHANG Dan, WANG W. Fault diagnosis of rolling element bearings based on EMD and MKD[J]. Journal of Vibration and Shock, 2015, 34(9): 55-59, 64. (in Chinese) doi: 10.13465/j.cnki.jvs.2015.09.010 [11] 丁承君, 冯玉伯, 王曼娜. 基于变分模态分解与深度卷积神经网络的滚动轴承故障诊断[J]. 振动与冲击, 2021, 40(2): 287-296. DING Chengjun, FENG Yubo, WANG Manna. Rolling bearing fault diagnosis using variational mode decomposition and deep convolutional neural network[J]. Journal of Vibration and Shock, 2021, 40(2): 287-296. (in Chinese doi: 10.13465/j.cnki.jvs.2021.02.039DING Chengjun, FENG Yubo, WANG Manna. Rolling bearing fault diagnosis using variational mode decomposition and deep convolutional neural network[J]. Journal of Vibration and Shock, 2021, 40(2): 287-296. (in Chinese) doi: 10.13465/j.cnki.jvs.2021.02.039 [12] 栾孝驰, 张振鹏, 沙云东, 等. 基于优化变分模态分解与计算阶次分析的主轴承故障特征增强方法[J]. 推进技术, 2024, 45(11): 2312085. LUAN Xiaochi, ZHANG Zhenpeng, SHA Yundong, et al. Main bearing fault feature enhancement method based on optimal variational mode decomposition and computational order analysis[J]. Journal of Propulsion Technology, 2024, 45(11): 2312085. (in Chinese doi: 10.13675/j.cnki.tjjs.2312085LUAN Xiaochi, ZHANG Zhenpeng, SHA Yundong, et al. Main bearing fault feature enhancement method based on optimal variational mode decomposition and computational order analysis[J]. Journal of Propulsion Technology, 2024, 45(11): 2312085. (in Chinese) doi: 10.13675/j.cnki.tjjs.2312085 [13] LUAN Xiaochi, ZHAO Junhao, SHA Yundong, et al. Multi-channel vibration information weighted fusion for fault feature extraction of rotating machinery main bearings[J]. Mechanical Systems and Signal Processing, 2025, 228: 112476. doi: 10.1016/j.ymssp.2025.112476 [14] DAI Xin, YI Kang, WANG Fuling, et al. Bearing fault diagnosis based on POA-VMD with GADF-Swin Transformer transfer learning network[J]. Measurement, 2024, 238: 115328. doi: 10.1016/j.measurement.2024.115328 [15] LUAN Xiaochi, ZHONG Chenghao, ZHAO Fengtong, et al. Bearing fault damage degree identification method based on SSA-VMD and Shannon entropy–exponential entropy decision[J]. Structural Health Monitoring, 2024, 23(5): 3105-3133. doi: 10.1177/14759217231219710 [16] 沙云东, 赵宇, 栾孝驰, 等. 基于多参数信息融合筛选的滚动轴承振动信号特征提取与表征方法[J]. 推进技术, 2023, 44(7): 2205050. SHA Yundong, ZHAO Yu, LUAN Xiaochi, et al. Feature extraction and characterization of rolling bearing vibration signal based on multi parameter information fusion and screening[J]. Journal of Propulsion Technology, 2023, 44(7): 2205050. (in Chinese doi: 10.13675/j.cnki.tjjs.2205050SHA Yundong, ZHAO Yu, LUAN Xiaochi, et al. Feature extraction and characterization of rolling bearing vibration signal based on multi parameter information fusion and screening[J]. Journal of Propulsion Technology, 2023, 44(7): 2205050. (in Chinese) doi: 10.13675/j.cnki.tjjs.2205050 [17] 栾孝驰, 张席, 沙云东, 等. 基于灰狼算法优化极限学习机的中介轴承故障诊断方法[J]. 推进技术, 2024, 45(4): 2205105. LUAN Xiaochi, ZHANG Xi, SHA Yundong, et al. Method on inter-Shaft bearing fault diagnosis based on extreme learning machine optimized by gray wolf optimization[J]. Journal of Propulsion Technology, 2024, 45(4): 2205105. (in Chinese doi: 10.13675/j.cnki.tjjs.2205105LUAN Xiaochi, ZHANG Xi, SHA Yundong, et al. Method on inter-Shaft bearing fault diagnosis based on extreme learning machine optimized by gray wolf optimization[J]. Journal of Propulsion Technology, 2024, 45(4): 2205105. (in Chinese) doi: 10.13675/j.cnki.tjjs.2205105 [18] MIAO Yonghao, ZHANG Boyao, LI Chenhui, et al. Feature mode decomposition: new decomposition theory for rotating machinery fault diagnosis[J]. IEEE Transactions on Industrial Electronics, 2023, 70(2): 1949-1960. doi: 10.1109/TIE.2022.3156156 [19] 鄢小安, 贾民平. 基于参数自适应特征模态分解的滚动轴承故障诊断方法[J]. 仪器仪表学报, 2022, 43(10): 252-259. YAN Xiaoan, JIA Minping. A rolling bearing fault diagnosis method based on parameter-adaptive feature mode decomposition[J]. Chinese Journal of Scientific Instrument, 2022, 43(10): 252-259. (in Chinese doi: 10.19650/j.cnki.cjsi.J2210053YAN Xiaoan, JIA Minping. A rolling bearing fault diagnosis method based on parameter-adaptive feature mode decomposition[J]. Chinese Journal of Scientific Instrument, 2022, 43(10): 252-259. (in Chinese) doi: 10.19650/j.cnki.cjsi.J2210053 [20] 栾孝驰, 李彦徵, 徐石, 等. 基于小波包变换与CEEMDAN的滚动轴承故障诊断方法[J]. 航空动力学报, 2024, 39(5): 20220473. LUAN Xiaochi, LI Yanzheng, XU Shi, et al. Rolling bearing fault diagnosis method based on wavelet packet transform and CEEMDAN[J]. Journal of Aerospace Power, 2024, 39(5): 20220473. (in Chinese doi: 10.13224/j.cnki.jasp.20220473LUAN Xiaochi, LI Yanzheng, XU Shi, et al. Rolling bearing fault diagnosis method based on wavelet packet transform and CEEMDAN[J]. Journal of Aerospace Power, 2024, 39(5): 20220473. (in Chinese) doi: 10.13224/j.cnki.jasp.20220473 [21] SMITH W A, RANDALL R B. Rolling element bearing diagnostics using the Case Western Reserve University data: a benchmark study[J]. Mechanical Systems and Signal Processing, 2015, 64/65: 100-131. [22] 佟鑫宇, 沙云东, 栾孝驰, 等. 基于声发射参数综合分析的滚动轴承典型故障识别方法[J]. 燃气涡轮试验与研究, 2023, 36(6): 35-41. TONG Xinyu, SHA Yundong, LUAN Xiaochi, et al. Identification of typical rolling bearing faults based on acoustic emission parameters[J]. Gas Turbine Experiment and Research, 2023, 36(6): 35-41. (in Chinese doi: 10.3969/j.issn.1672-2620.2023.06.006TONG Xinyu, SHA Yundong, LUAN Xiaochi, et al. Identification of typical rolling bearing faults based on acoustic emission parameters[J]. Gas Turbine Experiment and Research, 2023, 36(6): 35-41. (in Chinese) doi: 10.3969/j.issn.1672-2620.2023.06.006 -
点击查看大图
计量
- 文章访问数: 194
- HTML浏览量: 70
- PDF量: 18
- 被引次数: 0