Application of SOM and EWMA in Fault Prediction of Rolling Linear Guideway
-
摘要: 提出了一种基于机器学习的滚动直线导轨故障预测集成方法。首先，通过寿命试验，对由三轴加速度传感器采集的振动信号进行小波包分解，提取分部能量作为信号特征；其次，运用提取的特征训练自组织映射(Self-organizing map，SOM)神经网络，应用训练后的SOM识别线轨健康状态；最后，使用最小量化误差与指数加权移动平均控制图(Exponentially weighted moving-average，EWMA)实现动态故障预警。该方法将SOM与小波包分解相结合，选用最小量化误差构建EWMA控制图，解决了线轨状态监测可视化与疲劳程度数值评定问题，验证了该集成方法用于直线导轨故障预测的有效性。Abstract: This paper presents a machine learning based fault prediction integration method for rolling linear guideway. Firstly, through the life test, the vibration signals collected by the triaxial acceleration sensor have been decomposed by wavelet packet, and the partial energy has been extracted as the signal feature. Secondly, the SOM (self organizing map) neural network has been trained by the extracted feature, and the trained SOM has been applied to identify the health status of the railway. Finally, the minimum quantization error and EWMA (exponential weighted moving average control chart) have been used to realize dynamic fault early warning. This method combines SOM with wavelet packet decomposition, selects the minimum quantization error to build EWMA control chart, solves the problems of visual monitoring and numerical evaluation of fatigue degree, and the effectiveness of the integrated method for fault prediction of linear guideway was verified.
-
表 1 滚动直线导轨寿命试验数据概览
试验线轨序号 出现故障时观察组序数 出现故障时已运行距离/km 试验批次 所属组别 1 105 2 127 1 训练组 2 116 2 553 1 测试组 3 78 1 563 1 验证组 4 114 2 482 1 训练组 5 90 1 816 1 验证组 6 68 1 352 1 训练组 7 85 1 728 1 测试组 8 96 1 909 1 验证组 9 54 1 086 2 训练组 10 64 1 236 2 测试组 11 74 1 473 2 验证组 12 85 1 708 2 验证组 13 61 1 187 2 训练组 14 97 1 920 2 测试组 15 79 1 602 2 验证组 16 88 1 773 2 测试组 17 58 1 167 3 验证组 18 111 2 466 3 测试组 19 93 1 864 3 训练组 20 82 1 651 3 验证组 21 106 2 148 3 训练组 22 30 463 3 测试组 23 99 1 966 3 测试组 24 95 1 893 3 训练组 
下载: 导出CSV
表 2 测试组与验证组试件故障预警概况
试验线轨序号 触发故障预警时观察组序数 触发故障预警时已运行距离/km 实际出现故障时观察组序数 实际出现故障时已运行距离/km 触发故障预警时剩余寿命/km 组别 2 112 2 340 116 2553 213 测试组 7 84 1 680 85 1728 48 测试组 10 55 1 106 64 1236 130 测试组 14 82 1 642 97 1920 278 测试组 16 85 1 726 88 1773 47 测试组 18 75 1 492 111 2466 974 测试组 22 28 432 30 463 31 测试组 23 93 1 864 99 1966 102 测试组 3 75 1 502 78 1563 61 验证组 5 89 1 796 90 1816 20 验证组 8 82 1 631 96 1909 278 验证组 11 69 1 370 74 1473 103 验证组 12 61 1 222 85 1708 486 验证组 15 76 1 540 79 1602 62 验证组 17 56 1 125 58 1167 42 验证组 20 78 1 570 82 1651 81 验证组
下载: 导出CSV
-
[1] ZOU H T, WANG B L. Investigation of the contact stiffness variation of linear rolling guides due to the effects of friction and wear during operation[J]. Tribology International, 2015, 92: 472-484 doi: 10.1016/j.triboint.2015.07.005 [2] ZHENG J D, PAN H Y, CHENG J S. Rolling bearing fault detection and diagnosis based on composite multiscale fuzzy entropy and ensemble support vector machines[J]. Mechanical Systems and Signal Processing, 2017, 85: 746-759 doi: 10.1016/j.ymssp.2016.09.010 [3] SAUCEDO-DORANTES J J, DELGADO-PRIETO M, ORTEGA-REDONDO J A, et al. Multiple-fault detection methodology based on vibration and current analysis applied to bearings in induction motors and gearboxes on the kinematic chain[J]. Shock and Vibration, 2016, 2016: 5467643 [4] FENG H T, CHEN R, WANG Y W. Feature extraction for fault diagnosis based on wavelet packet decomposition: an application on linear rolling guide[J]. Advances in Mechanical Engineering, 2018, 10(8): 1-12 [5] 李娟娟, 孟国营, 谢广明, 等. 基于小波包与SOM神经网络的传感器故障诊断[J]. 传感技术学报, 2017, 30(7): 1035-1039 doi: 10.3969/j.issn.1004-1699.2017.07.011LI J J, MENG G Y, Xie G M, et al. Sensor fault diagnosis based on wavelet packet and SOM neural network[J]. Chinese Journal of Sensors and Actuators, 2017, 30(7): 1035-1039 (in Chinese) doi: 10.3969/j.issn.1004-1699.2017.07.011 [6] 夏筱筠, 林浒. 基于自学习SOM和ARMA算法的数控机床滚动轴承健康预警研究[J]. 小型微型计算机系统, 2019, 40(1): 215-220 https://www.cnki.com.cn/Article/CJFDTOTAL-XXWX201901042.htmXIA X J, LIN H. Research on health warning for rolling bearing of CNC machine tool based on self-learning SOM and ARMA algorithm[J]. Journal of Chinese Computer Systems, 2019, 40(1): 215-220 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XXWX201901042.htm [7] BIANCHINI C, IMMOVILLI F, COCCONCELLI M, et al. Fault detection of linear bearings in brushless AC linear motors by vibration analysis[J]. IEEE Transactions on Industrial Electronics, 2011, 58(5): 1684-1694 doi: 10.1109/TIE.2010.2098354 [8] JÄMSÄ-JOUNELA S L, VERMASVUORI M, ENDÉN P, et al. A process monitoring system based on the Kohonen self-organizing maps[J]. Control Engineering Practice, 2003, 11(1): 83-92 doi: 10.1016/S0967-0661(02)00141-7 [9] QIU H, LEE J, LIN J, et al. Robust performance degradation assessment methods for enhanced rolling element bearing prognostics[J]. Advanced Engineering Informatics, 2003, 17(3-4): 127-140 doi: 10.1016/j.aei.2004.08.001 [10] HUANG R Q, XI L F, LI X L, et al. Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods[J]. Mechanical Systems and Signal Processing, 2007, 21(1): 193-207 doi: 10.1016/j.ymssp.2005.11.008 [11] ROBERTS S W. Control chart tests based on geometric moving averages[J]. Technometrics, 1959, 1(3): 239-250 doi: 10.1080/00401706.1959.10489860 [12] WU H, DAI Y, WANG C, et al. Identification and forewarning of GNSS deformation information based on a modified EWMA control chart[J]. Measurement, 2020, 160: 107854 doi: 10.1016/j.measurement.2020.107854 [13] QIU P H. Introduction to statistical process control[M]. Boca Raton: Chapman and Hall/CRC, 2013 [14] MONTGOMERY D C. Introduction to statistical quality control[M]. 6th ed. John Wiley & Sons, Inc., 2009 [15] 丁宸宇, 岳瑞华, 李远冬. 修正EWMA控制图在MAP中的应用[J]. 火力与指挥控制, 2019, 44(9): 78-82, 87 https://www.cnki.com.cn/Article/CJFDTOTAL-HLYZ201909015.htmDING C Y, YUE R H, LI Y D. Application of modified EWMA control chart in MAP[J]. Fire Control & Command Control, 2019, 44(9): 78-82, 87 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-HLYZ201909015.htm [16] VATANEN T, OSMALA M, RAIKO T, et al. Self- organization and missing values in SOM and GTM[J]. Neurocomputing, Vol. 147, 60-70, 2015 doi: 10.1016/j.neucom.2014.02.061 [17] VESANTO J. Neural network tool for data mining: SOM toolbox[C]//TOOLMET 2000 Symposium-Tool Environments and Development Methods for Intelligent Systems. Oulu, Finland, 2000 -
点击查看大图
图(12) / 表(2)
计量
- 文章访问数: 132
- HTML全文浏览量: 31
- PDF下载量: 16
- 被引次数: 0
