基于VMD能量熵与优化支持向量机的轴承故障诊断

doi:10.3969/j.issn.1000-1158.2021.07.11

摘要
图/表
参考文献(25)
相关文章 (15)

全文: PDF (3647 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要滚动轴承早期故障信号比较微弱,且受噪声与振动耦合影响,导致其故障判别失准。基于变分模态分解算法(VMD)与能量熵结合构建多模态特征矩阵,以灰狼算法(GWO)优化支持向量机(SVM)参数,提出VMD-Entropy-OSVM轴承智能故障诊断,采用轴承实验数据验证所提方法的有效性与优越性。实验结果表明:VMD-Entropy-OSVM不仅可识别轴承损伤末期的不同故障类型,且在识别损伤初期亦有较高准确度;在信噪比为8dB下准确率高达99.8%,比现有方法提高3.3%～27.3%;当信噪比为0dB下仍有73.5%的准确度,比现有方法提高11%～33%,该模型表现出良好的泛化性能;在相同计算资源下,所需运行时间更短,效率更高。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	金江涛
	许子非
	李春
	缪维跑
	李根

关键词 ：计量学;智能故障诊断, 滚动轴承, 变分模态分解;能量熵;灰狼算法;支持向量机;优化

Abstract：The early fault signals of rolling bearings are relatively weak, and are affected by the coupling of noise and vibration, which leads to inaccurate fault judgments. Based on variational mode decomposition (VMD) and energy entropy, multi-mode characteristic matrix is constructed. Grey wolf optimizer (GWO) is adopted to optimize the parameters of support vector machine (SVM). VMD-Entropy-OSVM bearing intelligent fault diagnosis is proposed, using bearing experimental data to verify the effectiveness and superiority of the proposed method. The experimental results show that VMD-Entropy-OSVM not only recognizes different fault types at the end of bearing damage, but also has high accuracy at the beginning of bearing damage. The accuracy of the proposed method is up to 99.8% at 8dB, which is 3.3%～27.3% higher than the existing method. When the SNR is 0dB, the accuracy is still 73.5%, which is 11%～33% higher than the existing method, the model shows good generalization performance. In addition, the running time is shorter and more efficient under the same computing resources.

Key words： metrology intelligent fault diagnosis rolling bearing variational mode decomposition energy entropy grey wolf optimizer support vector machine optimization

收稿日期: 2020-06-09 发布日期: 2021-07-15

PACS:	TB936
	TB973

基金资助:国家自然科学基金(51976131,51676131);上海市“科技创新行动计划”地方院校能力建设项目(19060502200)

通讯作者: 李春(1963-),男,北京人,上海理工大学教授、博士生导师,主要从事流体机械优化设计、风能利用等方面研究工作。Email: lichunusst@163.com E-mail: lichun_usst@163.com

作者简介: 金江涛(1996-),男,浙江金华人,上海理工大学硕士研究生,主要研究方向为风电传动部件故障诊断及信号处理。Email: lese0808@163.com

引用本文:

金江涛,许子非,李春,缪维跑,李根. 基于VMD能量熵与优化支持向量机的轴承故障诊断[J]. 计量学报, 2021, 42(7): 898-905.
JIN Jiang-tao,XU Zi-fei,LI Chun,MIAO Wei-pao,LI Gen. Bearing Fault Diagnosis Based on VMD Energy Entropy and Optimized Support Vector Machine. Acta Metrologica Sinica, 2021, 42(7): 898-905.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2021.07.11 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2021/V42/I7/898

［1］Qiao W, Lu D. A survey on wind turbine condition monitoring and fault diagnosis-Part Ⅱ: signals and signal processing methods［J］. IEEE Transactions on Industrial Electronics, 2015, 62(10): 1-12.
［2］Ozgener O, Ozgener L. Exergy and reliability analysis of wind turbine systems: A case study ［J］. Renewable & Sustainable Energy Reviews, 2007, 11(8): 1811-1826.
［3］陈雪峰, 李继猛, 程航, 等. 风力发电机状态监测和故障诊断技术的研究与进展［J］. 机械工程学报, 2011, 47(9): 45-52.
Chen X F, Li J M, Cheng H, et al. Research and development of wind turbine condition monitoring and fault diagnosis technology［J］. Journal of Mechanical Engineering, 2011, 47(9): 45-52.
［4］Talhaoui H, Menacer A, Kessal A, et al. Fast Fourier and discrete wavelet transforms applied to sensorless vector control induction motor for rotor bar faults diagnosis［J］. Isa Transactions, 2014, 53(5): 1639-1649.
［5］汪朝海, 蔡晋辉, 曾九孙. 基于经验模态分解和主成分分析的滚动轴承故障诊断研究［J］. 计量学报, 2019, 40(6): 1077-1082.
Wang C H, Cai J H, Zeng J S. Research on fault diagnosis of rolling bearing based on Empirical Mode Decomposition and principal component analysis［J］. Acta Metrologica Sinica, 2019, 40(6): 1077-1082.
［6］董文智, 张超. 基于EEMD分解和奇异值差分谱理论的轴承故障诊断研究［J］. 机械强度, 2012, 34(2): 183-189.
Dong W Z, Zhang C. Bearing fault diagnosis based on EEMD and singular value difference spectrum theory［J］. Journal of Mechanical Strength, 2012, 34(2): 183-189.
［7］马洪斌. 基于变分模态分解的滚动轴承故障检测方法研究［D］. 北京: 北京交通大学, 2018.
［8］Hua L, Tao L, Xing W, et al. Application of EEMD and improved frequency band entropy in bearing fault feature extraction［J］. ISA Transactions, 2019, 88(2): 170-185.
［9］Dragomiretskiy K, Zosso D. Variational Mode Decomposition［J］. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.
［10］Huang Y, Lin J H, Liu Z C, et al. A modified scale-space guiding variational mode decomposition for high-speed railway bearing fault diagnosis［J］. Journal of Sound and Vibration, 2019, 444(1): 216-234.
［11］Dong W, Yang Z, Cai Y, et al. Sparsity guided empirical wavelet transform for fault diagnosis of rolling element bearings［J］. Mechanical Systems and Signal Processing, 2018, 101(2): 292-308.
［12］杨秋玉, 阮江军, 黄道春, 等. 基于VMD-Hilbert边际谱能量熵和SVM的高压断路器机械故障诊断［J］. 电机与控制学报, 2020, 24(3): 11-19.
Yang Q Y, Ruan J J, Huang D C, et al. Mechanical fault diagnosis for high voltage circuit breakers based on VMD-Hilbert marginal spectrum energy entropy and SVM［J］. Electric Machines and Control, 2020, 24(3): 11-19.
［13］辛李霞, 汪建新, 苏晓云. 基于VMD和最小熵反褶积的齿轮早期故障诊断［J］. 机械设计与制造, 2019,(6): 50-54.
Xin L X, Wang J X, Su X Y. Early Fault Diagnosis of Gear Based on VMD and Minimum Entropy Deconvolution［J］. Machinery Design & Manufacture, 2019,(6): 50-54.
［14］Guo H, Wang W. An active learning-based SVM multi-class classification model［J］. Pattern Recognition, 2015, 48(5): 1577-1597.
［15］Gaudioso M, Gorgone E, Labbe M, et al. Lagrangian relaxation for SVM feature selection［J］. Computers & Operations Research, 2017, 87(1): 137-145.
［16］Zhang M J, Chai K. Combined improved EEMD with SVM in the bearing low dimensional small sample fault diagnosis［J］. Applied Mechanics and Materials, 2013, 427(1): 354-357.
［17］王宜静, 谭海燕. 基于多维度互近似熵的滚动轴承故障诊断方法研究［J］. 机械设计与研究, 2019, 35(1): 110-112,124.
Wang Y J, Tan H Y. Research on Fault Diagnosis Method of Rolling Bearing Based on Multi-dimension Cross Approximate Entropy［J］. Machine Design & Research, 2019, 35(1): 110-112,124.
［18］张少波, 张海霞. 基于IITD样本熵和支持向量机的齿轮故障诊断方法［J］. 机械设计与制造, 2017,(12): 212-215,219.
Zhang S B, Zhang H X. A Gear Fault Diagnosis Method Based on IITD Sample Entropy and SVM［J］. Machinery Design & Manufacture, 2017,(12): 212-215,219.
［19］时培明, 梁凯, 赵娜, 等. 基于分形维数和GA-SVM的风电机组齿轮箱轴承故障诊断［J］. 计量学报, 2018, 39(1): 61-65.
Shi P M, Liang K, Zhao N, et al. Fault Diagnosis of Wind Turbine Gearbox Bearing Based on Fractal Dimension and GA-SVM［J］. Acta Metrologica Sinica, 2018, 39(1): 61-65.
［20］吴飞, 丁军, 刘苏行, 等. 基于VMD和PSO-SVM的汽车传动轴系故障诊断［J］. 机械传动, 2019, 43(8): 120-124.
Wu F, Ding J, Liu S X, et al. Fault Diagnosis of Transmission Shaft System of Automobile based on VMD and PSO-SVM［J］. Journal of Mechanical Transmission, 2019, 43(8): 120-124.
［21］Bengio Y, Courville A, Vincent P. Representation Learning: A Review and New Perspectives［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8): 1798-1828.
［22］刘洋, 曹云东, 侯春光. 基于经验模态分解及维格纳威尔分布的电缆双端故障定位算法［J］. 中国电机工程学报, 2015, 35(16): 4086-4093.
Liu Y, Cao Y D, Hou C G. The Cable Two-terminal Fault Location Algorithm Based on EMD and WVD［J］. Proceedings of the CSEE, 2015, 35(16): 4086-4093.
［23］Mirjalili S, Mirjalili S M, Lewis A. Grey Wolf Optimizer［J］. Advances in Engineering Software, 2014, 69: 46-61.
［24］Gu R, Chen J, Hong L J, et al. Incipient fault diagnosis of rolling bearings based on adaptive variational mode decomposition and Teager energy operator［J］. Measurement, 2020, 149: 1-13.
［25］Wang B, Lei Y G, Li N P, et al. A hybrid prognostics approach for estimating remaining useful life of rolling element bearings［J］. IEEE Transactions on Reliability, 2018, 69(1): 401-412.