|
|
|
| Fault feature extraction of spindle bearing based on SSD and MI |
| WANG Zhenya1,2, WU Xing2,3, LIU Tao1,2, MIAO Hu4 |
1.Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming 650500, China;
2.Key Laboratory of Advanced Equipment Intelligent Manufacturing Technology of Yunnan Province, Kunming 650500, China;
3.Yunnan Mechanical and Electrical Vocational Technical College, Kunming 650500, China;
4.Kunming Yunnei Power Co., Ltd, Kunming 650500, China |
|
|
|
|
Abstract Singular spectrum decomposition (SSD) algorithm has the problems of poor noise reduction ability when the signal-to-noise ratio is low and the number of sensitive components is difficult to determine. Aiming at the above problems, a spindle fault feature extraction method based on SSD Mutual Information (MI) is proposed. Firstly, the bearing vibration signal is decomposed by SSD to obtain multiple singular spectral components (SSCs); Then calculate the mutual information between the original signal and SSC respectively, and select the component at the minimum mutual information (MinMI) as the best component. Due to the influence of background noise, the selected optimal component fault characteristic frequency is not obvious. Therefore, based on the characteristics of vibration signals and mutual information theory, a method to retain the effective components of differential mutation mutual information (DMMI) is proposed. By calculating the MI value between the sum of adjacent SSCs, the components in the mutation point are retained as sensitive signals. On this basis, a band-pass filter is designed according to the MinMI principle to filter the sensitive signal band-pass and envelope demodulation to extract the fault characteristic frequency. The analysis of the simulation signal and real spindle-bearing data shows that DMMI preserving sensitive components of the signal combined with MinMI adaptive filtering processing has an excellent performance in the spindle-bearing fault feature extraction.
|
|
Received: 14 December 2022
Published: 15 August 2023
|
|
|
|
[1] Lei Y G, YANG B, Jiang X W, et al. Applications of machine learning to machine fault diagnosis: A review and roadmap [J]. Mechanical System and Signal Processing, 2020, 138: 106587-106625.
[2] 李霁蒲, 黄如意, 陈祝云, 等. 一种用于主轴轴承故障诊断的深度卷积动态对抗迁移网络[J]. 振动工程学报, 2022, 1(02): 446-453.
LI Jipu, HUANG Ruyi, CHEN Zhuyun, et al. A deep convolutional dynamic adversarial transfer network for spindle bearing fault diagnosis [J]. Journal of Vibration Engineering, 2022, 1(02): 446-453.
[3] 甄冬, 田少宁, 郭俊超, 孟召宗, 谷丰收. 改进型EEMD和MSB解调方法及其在轴承故障特征提取中的应用[J/OL].（2022-04-22）[2022-12-14]. https://kns.cnki.net/kcms/detail/32.1349.TB.20220421.1125.004.html.
[4] 赵博, 李鹤. 结合EMD和LSF的振动信号降噪方法的研究[J]. 振动.测试与诊断, 2022, 42(03): 606-616.
ZhAO Bo, LI He. Noise reduction method of vibration signal combining EMD and LSF [J]. Journal of Vibration, Measurement and Diagnosis, 2022, 42(03): 606-616.
[5] GANGSAR P, TIWARI R J M S, PROCESSING S. Signal based condition monitoring techniques for fault detection and diagnosis of induction motors: A state-of-the-art review [J]. Mechanical System and Signal Processing, 2020, 144(4): 106908-106928.
[6] 李华, 刘韬, 伍星, 等. 相关奇异值比的SVD在轴承故障诊断中的应用[J]. 机械工程学报, 2021, 57(21): 138-149.
LI Hua, LIU Tao, WU Xing, et al. Application of SVD with Correlation Singular Value Ratio in Bearing Fault Diagnosis [J]. Journal of Mechanical Engineering, 2021, 57(21): 138-149.
[7] Li Hua, Liu Tao, Wu Xing, et al. Application of EEMD and improved frequency band entropy in bearing fault feature extraction [J]. ISA Transactions, 2019, 88: 170-185
[8] 崔玲丽, 刘银行, 王鑫. 基于改进奇异值分解的滚动轴承微弱故障特征提取方法[J]. 机械工程学报, 2022, 28 (02): 1-12.
CUI Lingli, LIU Bank, WANG Xin. Feature extraction of weak fault for rolling bearing based on improved
singular value decomposition [J]. Journal of Mechanical Engineering, 2022, 28 (02): 1-12.
[9] 程铁栋, 易其文, 吴义文, 等. 改进EWT_MPE模型在矿山微震信号特征提取中的应用[J]. 振动与冲击, 2021, 40(09): 92-101.
CHENG Tiedong, YI Qiwen, WU Yiwen, et al. Application of improved EWT_MPE model in feature extraction of mine micro-seismic signals [J]. Journal of Vibration and Shock, 2021, 40(09): 92-101.
[10] 于淼, 张耀鲁, 徐泽辰, 等. 基于MEEMD-HHT的分布式光纤振动传感系统信号特征提取方法[J]. 红外与激光工程, 2021, 50(07): 207-218.
Yu Miao, Zhang Yaolu, Xu Zechen, et al. Signal feature extraction method based on MEEMD-HHT distributed optical fiber vibration sensing system [J]. Infrared and Laser Engineering, 2021, 50(07): 207-218.
[11] Bonizzi P, Karel J, Mesta O, et al. SINGULAR SPECTRUM DECOMPOSITION: A NEW METHOD FOR TIME SERIES DECOMPOSITION[J]. Advances in Adaptive Data Analysis, 2014, 6(04):107-109.
[12] 王晓龙, 唐贵基, 何玉灵, 等. 变转速工况下基于改进奇异谱分解和1.5维包络阶次谱的风电机组轴承损伤识别[J]. 太阳能学报, 2021, 42(01): 240-247.
WANG Xiaolong, TANG Guiji, HE Yuling, et al. Injury identification of wind turbine bearing based on ISSD and 1.5 dimension envelope order spectrum under variable rotating speed condition [J]. Acta Energiae Solaris Sinica, 2021, 42(01): 240-247.
[13] 周杰, 王云艺, 陈传海, 等. 基于改进MED-SSD的齿轮箱复合故障诊断方法[J]. 吉林大学学报(工学版), 2022, 52(02): 450-457.
ZHOU Jie, WANG Yunyi, CHEN Chuanhai, et al. Gearbox complex fault diagnosis method based on improved minimum entropy deconvolution and singular spectrum decomposition [J]. Journal of Jilin University (Engineering and Technology Edition), 2022, 52(02): 450-457.
[14] 陈是扦, 彭志科, 周鹏. 信号分解及其在机械故障诊断中的应用研究综述[J]. 机械工程学报, 2020, 56(17): 91-107.
CHEN Shijian, PENG Zhike, ZHOU Peng. Review of signal decomposition theory and its applications in machine fault diagnosis [J]. Chinese Journal of Mechanical Engineering, 2020, 56(17): 91-107.
[15] Peng H, Long F, Ding C. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2005, 27(8):1226-1238.
[16] Li Hua, Liu Tao, Wu Xing, et al. Research on bearing fault feature extraction based on singular value decomposition and optimized frequency band entropy[J]. Mechanical Systems and Signal Processing, 2019, 118: 477-502
[17] Miao Y, Zhao M, Hua J. Research on sparsity indexes for fault diagnosis of rotating machinery [J]. Measurement, 2020, 158:107733-107745.
[18] 张旭辉, 张超, 樊红卫, 等. 快速谱峭度结合阶次分析滚动轴承故障诊断[J]. 振动.测试与诊断, 2021, 41(06): 235-242.
ZHANG Xuhui, ZHNAG Chao, FAN Hongwei, et al. Improved fault diagnosis of rolling bearing by fast kurtogram and order analysis [J]. Journal of Vibration，Measurement & Diagnosis, 2021, 41(06): 235-242.
|
| [1] |
. [J]. JOURNAL OF VIBRATION AND SHOCK, 2024, 43(7): 30-. |
|
|
|
|
