A Rolling Bearing Fault Diagnosis Method of Time-shifted Multi-scale Permutation Entropy Combining with ELM
-
摘要: 多尺度排列熵(Multi-scale permutation entropy, MPE)随着尺度因子的增加得到的粗粒化序列长度越来越短,造成时间序列信息的严重损失。为此,提出了时移多尺度排列熵(Time-shifted multi-scale permutation entropy, TSMPE)。首先,采用仿真信号分别对TSMPE与MPE做仿真对比分析,结果表明,TSMPE对原始振动信号的长度依赖性较小,得到的熵值更加稳定。进一步地,提出了一种基于TSMPE与极限学习机的滚动轴承故障检测与诊断方法,将其应用于两组实际滚动轴承测试数据对滚动轴承故障类型和程度进行识别, 结果表明:所提出故障诊断方法不仅能够准确地诊断滚动轴承的故障类型和程度,而且识别率高于基于MPE与ELM的故障诊断方法。Abstract: When using the Multi-scale Permutation Entropy (MPE), with the increase of the scale factor, the obtained coarse-grained time series becomes shorter and shorter, which results in serious loss of time series information. For this purpose, a new Time-shifted Multi-scale Permutation Entropy (TSMPE) is put forward in this study. Firstly, the comparison of TSMPE and MPE is carried out with simulated signal. The results show that TSMPE has less dependence on signal length and the obtained entropy value is more stable. Furthermore, based on TSMPE and extreme learning machine, a fault detection and diagnosis method for rolling bearing is proposed and applied to two testing data of actual rolling bearings to identify the fault types and degrees. The results show that the proposed fault diagnosis method can not only accurately diagnose the fault types and degrees of rolling bearings, but also the recognition rates are higher than the fault diagnosis methods based on MPE and ELM.
-
表 1 滚动轴承试验测试数据
故障类型 故障直径/mm 训练样本 测试样本 类型 滚动体故障1(BE1) 0.533 4 10 10 1 滚动体故障2(BE2) 0.177 8 10 10 2 内圈故障1(IR1) 0.533 4 10 10 3 内圈故障2(IR2) 0.177 8 10 10 4 外圈故障1(OR1) 0.533 4 10 10 5 外圈故障2(OR2) 0.177 8 10 10 6 正常(Norm) 0 10 10 7 表 2 滚动轴承试验测试数据
故障类型 故障直径/mm 训练样本 测试样本 类型 内圈故障1(IR1) 2 10 18 1 内圈故障2(IR2) 6 10 18 2 外圈故障1(OR1) 2 10 18 3 外圈故障2(OR2) 6 10 18 4 正常(Norm) 0 10 18 5 -
[1] ROMERO-SILVA R, MARSILLAC E, SHAABAN S, et al. Reducing the variability of inter-departure times of a single-server queueing system the effects of skewness[J]. Computers & Industrial Engineering, 2019, 135: 500-517 http://www.sciencedirect.com/science/article/pii/S0360835219303602 [2] 王吉林, 孟垂懿. 基于EEMD的变压器振动与声音信号IMF峭度特征量提取方法[J]. 水电能源科学, 2019, 37(9): 183-187 https://www.cnki.com.cn/Article/CJFDTOTAL-SDNY201909047.htmWANG J L, MENG C Y. Feature extraction method for transformer vibration and audio signal based on ensemble empirical mode decomposition[J]. Water Resources and Power, 2019, 37(9): 183-187 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-SDNY201909047.htm [3] 赵林桂, 詹渝明, 陈明涛. 基于傅里叶变换的异步电机转子故障检测[J]. 东北电力技术, 2004, 25(7): 9-11 doi: 10.3969/j.issn.1004-7913.2004.07.004ZHAO L G, ZHAN Y M, CHEN M T. Failure detection of asynchronous motor rotor bases on fourier transform[J]. Northeast Electric Power Technology, 2004, 25(7): 9-11 (in Chinese) doi: 10.3969/j.issn.1004-7913.2004.07.004 [4] XIN G, HAMZAOUI N, ANTONI J. Extraction of second-order cyclostationary sources by matching instantaneous power spectrum with stochastic model application to wind turbine gearbox[J]. Renewable Energy, 2020, 147: 1793-1758 http://ideas.repec.org/a/eee/renene/v147y2020ip1p1739-1758.html [5] 张西宁, 周融通, 郭清林, 等. 局部倒频谱编辑方法及其在齿轮箱微弱轴承故障特征提取中的应用[J]. 西安交通大学学报, 2019, 53(12): 1-9 https://www.cnki.com.cn/Article/CJFDTOTAL-XAJT201912001.htmZHANG X N, ZHOU R T, GUO Q L, et al. Local cepstral editing procedure with applications to slight gearbox bearing fault feature extraction[J]. Journal of Xi'an Jiaotong University, 2019, 53(12): 1-9 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XAJT201912001.htm [6] 张曹, 陈珺, 刘飞. 基于MCKD-EEMD近似熵和TWSVM的齿轮箱故障诊断[J]. 计算机测量与控制, 2017, 25(12): 13-16 https://www.cnki.com.cn/Article/CJFDTOTAL-JZCK201712004.htmZHANG C, CHEN J, LIU F. Gearbox fault diagnosis based on MCKD-EEMD-approximate entropy and TWSVM[J]. Computer Measurement & Control, 2017, 25(12): 13-16 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JZCK201712004.htm [7] 郑近德, 程军圣, 杨宇. 基于LCD和排列熵的滚动轴承故障诊断[J]. 振动、测试与诊断, 2014, 34(5): 802-806 doi: 10.3969/j.issn.1004-6801.2014.05.003ZHENG J D, CHENG J S, YANG Y. A rolling bearing fault diagnosis method based on LCD and permutation entropy[J]. Journal of Vibration, Measurement & Diagnosis, 2014, 34(5): 802-806 (in Chinese) doi: 10.3969/j.issn.1004-6801.2014.05.003 [8] 许凡, 方彦军, 张荣. 基于多尺度样本熵与PCA-FCM的滚动轴承故障诊断[J]. 青岛科技大学学报, 2017, 38(2): 100-106, 111 doi: 10.3969/j.issn.1671-8372.2017.02.019XU F, FANG Y J, ZHANG R. Rolling bearing fault diagnosis method based on multiscale sample entropy and PCA-FCM[J]. Journal of Qingdao University of Science and Technology, 2017, 38(2): 100-106, 111 (in Chinese) doi: 10.3969/j.issn.1671-8372.2017.02.019 [9] 李生鹏, 韦朋余, 丁峰, 等. 基于多尺度模糊熵和主成分分析的轴承故障特征提取[J]. 船舶力学, 2018, 22(10): 1277-1285 doi: 10.3969/j.issn.1007-7294.2018.10.012LI S P, WEI P Y, DING F, et al. Fault features extract of rolling bearing based on multiscale fuzzy entropy and principal component analysis[J]. Journal of Ship Mechanics, 2018, 22(10): 1277-1285 (in Chinese) doi: 10.3969/j.issn.1007-7294.2018.10.012 [10] 郑近德, 程军圣, 杨宇. 多尺度排列熵及其在滚动轴承故障诊断中的应用[J]. 中国机械工程, 2013, 24(19): 2641-2646 doi: 10.3969/j.issn.1004-132X.2013.19.017ZHENG J D, CHENG J S, YANG Y. Multi-scale permutation entropy and its applications to rolling bearing fault diagnosis[J]. China Mechanical Engineering, 2013, 24(19): 2641-2646 (in Chinese) doi: 10.3969/j.issn.1004-132X.2013.19.017 [11] 郑近德, 潘海洋, 徐培民, 等. 一种基于复合多尺度排列熵的滚动轴承故障诊断方法: 中国, CN104849050A[P]. 2015-08-19ZHENG J D, PAN H Y, XU P M, et al. Rolling bearing fault diagnosis method based on composite multi-scale permutation entropies: CN, CN104849050A[P]. 2015-08-19 [12] 郑近德, 刘涛, 孟瑞, 等. 基于广义复合多尺度排列熵与PCA的滚动轴承故障诊断方法[J]. 振动与冲击, 2018, 37(20): 61-66 https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ201820010.htmZHENG J D, LIU T, MENG R, et al. Generalized composite multiscale permutation entropy and PCA based fault diagnosis of rolling bearings[J]. Journal of Vibration and Shock, 2018, 37(20): 61-66 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ201820010.htm [13] 郑近德, 潘海洋, 童宝宏, 等. 基于VPMELM的滚动轴承劣化状态辨识方法[J]. 振动与冲击, 2017, 36(7): 57-61 https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ201707009.htmZHENG J D, PAN H Y, TONG B H, et al. A method for determining the deterioration of rolling bearings based on VPMELM[J]. Journal of Vibration and Shock, 2017, 36(7): 57-61 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCJ201707009.htm [14] SU X L, ZHANG S, YIN Y X, et al. Prediction model of hot metal temperature for blast furnace based on improved multi-layer extreme learning machine[J]. International Journal of Machine Learning and Cybernetics, 2019, 10(10): 2739-2752 doi: 10.1007/s13042-018-0897-3 [15] POTOĈNIK P, VIDRIH B, KITANOVSKI A, et al. Neural network, ARX, and extreme learning machine models for the short-term prediction of temperature in buildings[J]. Building Simulation, 2019, 12(6): 1077-1093 doi: 10.1007/s12273-019-0548-y [16] Bearing Data Center Website, Case Western Reserve University[DB/OL].[2017-06-20]. https://www.forbes.com/colleges/case-western-reserve-university/?sh=1d33d1682211 [17] JIANG X, WU N, SHI J J, et al. Instantaneous frequency estimation based on ridge information enhancement and feature fusion[J]. Journal of Vibration and Shock, 2018, 37(20): 171-177 http://www.researchgate.net/publication/330663042_Rotational_speed_estimation_based_on_the_ridge_enhancement_and_feature_fusion [18] QI Y M, SHEN C Q, WANG D, et al. Stacked sparse autoencoder-based deep network for fault diagnosis of rotating machinery[J]. IEEE Access, 2017, 5: 15066-15079 doi: 10.1109/ACCESS.2017.2728010