Fault diagnosis of rotating machinery based on multi-kernel supervised manifold learning
-
摘要:
为了准确地对旋转机械进行故障诊断,提出了一种多核监督流形学习算法(multi-kernel supervised manifold learning,MKSML)。MKSML算法可以有效地对高维故障数据进行特征选择,筛选出区分度高的低维故障特征。借助监督学习的思想,增强了同类样本的聚集性和不同类样本之间的差异性;同时基于所设计的多核函数提出了加权邻域图构建方法,能够保留近邻点之间的距离信息和角度信息,有效地抑制故障特征选择时样本中的异常值和噪声的干扰。通过灰狼优化算法调整MKSML算法相应的参数,使算法能够应用于不同类型的旋转机械故障诊断。在此基础上,建立了一种基于MKSML算法的旋转机械故障诊断模型,并进行了轴承故障诊断实验以及齿轮故障诊断实验。
Abstract:In order to accurately perform fault diagnosis for rotating machinery, a multi-kernel supervised manifold learning (MKSML) algorithm was proposed. More specifically, MKSML algorithm allowed to effectively select the features of high-dimensional fault data, and extract the low-dimensional fault features with better discrimination. Through the idea of supervised learning, the clustering of similar samples and the differences between various samples have been enhanced. A novel weighted neighborhood graph was proposed by constructing multi-kernel function. The distance information and angle information between adjacent points were retained. And the interference of outliers and noise in the sample was suppressed. Through the gray wolf optimization algorithm to adjust the MKSML parameters, the algorithm could be applied to various types of rotating machinery fault diagnosis. The fault diagnosis model of rotating machinery based on MKSML was proposed, and bearing fault diagnosis experiments and gear fault diagnosis experiments were conducted.
-
表 1 行星齿轮轴承故障诊断实验结果
Table 1. Experimental results of planet gear bearing fault diagnosis
降维方法 无故障/% 滚动体故障/% 外圈故障/% 内圈故障/% 平均/% MKSML 100.00 100.00 100.00 100.00 100.00 LVM 100.00 98.33 100.00 98.33 99.17 LLE 93.33 96.67 96.67 98.33 96.25 PCA 90.00 86.67 86.67 91.67 88.75 SAE 91.67 96.67 93.33 91.67 93.33 SOM 100.00 90.00 68.33 86.67 86.25 KLDA 93.33 86.67 91.67 90.00 90.42 MKSLLE 98.33 98.33 100.00 100.00 99.17 表 2 齿轮故障诊断实验结果
Table 2. Experimental results of gear fault diagnosis
降维方法 健康/% 缺齿/% 齿根裂纹/% 剥落/% 齿尖削平/% 平均/% MKSML 100.00 95.00 100.00 92.50 92.50 96.00 LVM 85.00 95.00 100.00 75.00 97.50 90.50 LLE 100.00 87.50 100.00 80.00 100.00 93.50 PCA 75.00 97.50 90.00 87.50 85.00 87.00 SAE 80.00 100.00 97.50 87.50 97.50 92.50 SOM 87.50 100.00 87.50 97.50 100.00 94.50 KLDA 85.00 100.00 100.00 100.00 90.00 95.00 MKSLLE 100.00 90.00 100.00 87.50 97.50 95.00 -
[1] DING Han,GAO R X,ISAKSSON A J,et al. State of AI-based monitoring in smart manufacturing and introduction to focused section[J]. IEEE/ASME Transactions on Mechatronics,2020,25(5): 2143-2154. doi: 10.1109/TMECH.2020.3022983 [2] 雷亚国,许学方,蔡潇,等. 面向机械装备健康监测的数据质量保障方法研究[J]. 机械工程学报,2021,57(4): 1-9. LEI Yaguo,XU Xuefang,CAI Xiao,et al. Research on data quality assurance for health condition monitoring of machinery[J]. Journal of Mechanical Engineering,2021,57(4): 1-9. (in Chinese doi: 10.3901/JME.2021.04.001LEI Yaguo, XU Xuefang, CAI Xiao, et al. Research on data quality assurance for health condition monitoring of machinery[J]. Journal of Mechanical Engineering, 2021, 57(4): 1-9. (in Chinese) doi: 10.3901/JME.2021.04.001 [3] 林京. 机器信息学: 机械产品智能化的学科支撑[J]. 机械工程学报,2021,57(2): 11-20. LIN Jing. Machinery informatics: a fundamental discipline to intelligent machinery[J]. Journal of Mechanical Engineering,2021,57(2): 11-20. (in Chinese doi: 10.3901/JME.2021.02.011LIN Jing. Machinery informatics: a fundamental discipline to intelligent machinery[J]. Journal of Mechanical Engineering, 2021, 57(2): 11-20. (in Chinese) doi: 10.3901/JME.2021.02.011 [4] LIU Ruonan,YANG Boyuan,ZIO E,et al. Artificial intelligence for fault diagnosis of rotating machinery: a review[J]. Mechanical Systems and Signal Processing,2018,108: 33-47. doi: 10.1016/j.ymssp.2018.02.016 [5] 叶壮,余建波. 基于多通道加权卷积神经网络的齿轮箱振动信号特征提取[J]. 机械工程学报,2021,57(1): 110-120. YE Zhuang,YU Jianbo. Feature extraction of gearbox vibration signals based on multi-channels weighted convolutional neural network[J]. Journal of Mechanical Engineering,2021,57(1): 110-120. (in Chinese doi: 10.3901/JME.2021.01.110YE Zhuang, YU Jianbo. Feature extraction of gearbox vibration signals based on multi-channels weighted convolutional neural network[J]. Journal of Mechanical Engineering, 2021, 57(1): 110-120. (in Chinese) doi: 10.3901/JME.2021.01.110 [6] MA Sai,CHU Fulei,HAN Qinkai. Deep residual learning with demodulated time-frequency features for fault diagnosis of planetary gearbox under nonstationary running conditions[J]. Mechanical Systems and Signal Processing,2019,127: 190-201. doi: 10.1016/j.ymssp.2019.02.055 [7] 侯文擎,叶鸣,李巍华. 基于改进堆叠降噪自编码的滚动轴承故障分类[J]. 机械工程学报,2018,54(7): 87-96. HOU Wenqing,YE Ming,LI Weihua. Rolling element bearing fault classification using improved stacked de-noising auto-encoders[J]. Journal of Mechanical Engineering,2018,54(7): 87-96. (in Chinese doi: 10.3901/JME.2018.07.087HOU Wenqing, YE Ming, LI Weihua. Rolling element bearing fault classification using improved stacked de-noising auto-encoders[J]. Journal of Mechanical Engineering, 2018, 54(7): 87-96. (in Chinese) doi: 10.3901/JME.2018.07.087 [8] 董绍江,裴雪武,汤宝平,等. 基于FNER性能退化指标及IDRSN的滚动轴承寿命状态识别方法[J]. 机械工程学报,2021,57(15): 105-115. DONG Shaojiang,PEI Xuewu,TANG Baoping,et al. Recognition of rolling bearing life status based on FNER performance degradation indicator and IDRSN[J]. Journal of Mechanical Engineering,2021,57(15): 105-115. (in Chinese doi: 10.3901/JME.2021.15.105DONG Shaojiang, PEI Xuewu, TANG Baoping, et al. Recognition of rolling bearing life status based on FNER performance degradation indicator and IDRSN[J]. Journal of Mechanical Engineering, 2021, 57(15): 105-115. (in Chinese) doi: 10.3901/JME.2021.15.105 [9] 郭庆,李印龙. 基于气路参数融合的涡扇发动机性能退化预测[J]. 航空动力学报,2021,36(11): 2251-2260. GUO Qing,LI Yinlong. Turbofan engine performance degradation prediction based on gas path parameter fusion[J]. Journal of Aerospace Power,2021,36(11): 2251-2260. (in ChineseGUO Qing, LI Yinlong. Turbofan engine performance degradation prediction based on gas path parameter fusion[J]. Journal of Aerospace Power, 2021, 36(11): 2251-2260. (in Chinese) [10] HE Liang,CHEN Xianhong,XU Can,et al. Local pairwise linear discriminant analysis for speaker verification[J]. IEEE Signal Processing Letters,2018,25(10): 1575-1579. doi: 10.1109/LSP.2018.2869107 [11] 戚晓利,王振亚,吴保林,等. 基于ACMPE、ISSL-Isomap和GWO-SVM的行星齿轮箱故障诊断[J]. 航空动力学报,2019,34(4): 744-755. QI Xiaoli,WANG Zhenya,WU Baolin,et al. Planetary gearbox fault diagnosis based on ACMPE,ISSL-Isomap and GWO-SVM[J]. Journal of Aerospace Power,2019,34(4): 744-755. (in ChineseQI Xiaoli, WANG Zhenya, WU Baolin, et al. Planetary gearbox fault diagnosis based on ACMPE, ISSL-Isomap and GWO-SVM[J]. Journal of Aerospace Power, 2019, 34(4): 744-755. (in Chinese) [12] ROWEIS S T,SAUL L K. Nonlinear dimensionality reduction by locally linear embedding[J]. Science,2000,290(5500): 2323-2326. doi: 10.1126/science.290.5500.2323 [13] BELKIN M,NIYOGI P. Laplacian eigenmaps for dimensionality reduction and data representation[J]. Neural Computation,2003,15(6): 1373-1396. doi: 10.1162/089976603321780317 [14] JIANG Quansheng,JIA Minping,HU Jianzhong,et al. Machinery fault diagnosis using su pervised manifold learning[J]. Mechanical Systems and Signal Processing,2009,23(7): 2301-2311. doi: 10.1016/j.ymssp.2009.02.006 [15] LI Benwei,ZHANG Yun. Supervised locally linear embedding projection (SLLEP) for machinery fault diagnosis[J]. Mechanical Systems and Signal Processing,2011,25(8): 3125-3134. doi: 10.1016/j.ymssp.2011.05.001 [16] SU Zuqiang,TANG Baoping,LIU Ziran,et al. Multi-fault diagnosis for rotating machinery based on orthogonal supervised linear local tangent space alignment and least square support vector machine[J]. Neurocomputing,2015,157: 208-222. doi: 10.1016/j.neucom.2015.01.016 [17] SAUL L K. A tractable latent variable model for nonlinear dimensionality reduction[J]. Proceedings of the National Academy of Sciences of the United States of America,2020,117(27): 15403-15408. [18] 罗林开,叶凌君,周绮凤. 常用核函数的几何度量与几何性质[J]. 厦门大学学报(自然科学版),2009,48(6): 804-807. LUO Linkai,YE Lingjun,ZHOU Qifeng. Geometric measures and properties of commonly used kernel functions[J]. Journal of Xiamen University (Natural Science),2009,48(6): 804-807. (in ChineseLUO Linkai, YE Lingjun, ZHOU Qifeng. Geometric measures and properties of commonly used kernel functions[J]. Journal of Xiamen University (Natural Science), 2009, 48(6): 804-807. (in Chinese) [19] MIRJALILI S,MIRJALILI S M,LEWIS A. Grey wolf optimizer[J]. Advances in Engineering Software,2014,69: 46-61. doi: 10.1016/j.advengsoft.2013.12.007 [20] 王晓龙,唐贵基,周福成. 自适应可调品质因子小波变换在轴承早期故障诊断中的应用[J]. 航空动力学报,2017,32(10): 2467-2475. WANG Xiaolong,TANG Guiji,ZHOU Fucheng. Application of adaptive tunable Q-factor wavelet transform on incipient fault diagnosis of bearing[J]. Journal of Aerospace Power,2017,32(10): 2467-2475. (in ChineseWANG Xiaolong, TANG Guiji, ZHOU Fucheng. Application of adaptive tunable Q-factor wavelet transform on incipient fault diagnosis of bearing[J]. Journal of Aerospace Power, 2017, 32(10): 2467-2475. (in Chinese) [21] ZHANG Shiqing. Enhanced supervised locally linear embedding[J]. Pattern Recognition Letters,2009,30(13): 1208-1218. doi: 10.1016/j.patrec.2009.05.011 [22] 洪骥宇,王华伟,倪晓梅. 基于降噪自编码器的航空发动机性能退化评估[J]. 航空动力学报,2018,33(8): 2041-2048. HONG Jiyu,WANG Huawei,NI Xiaomei. Assessment of performance degradation for aero-engine based on denoising autoencoder[J]. Journal of Aerospace Power,2018,33(8): 2041-2048. (in ChineseHONG Jiyu, WANG Huawei, NI Xiaomei. Assessment of performance degradation for aero-engine based on denoising autoencoder[J]. Journal of Aerospace Power, 2018, 33(8): 2041-2048. (in Chinese) [23] HAYAKAWA Y,OGATA T,SUGANO S. Flexible assembly work cooperating system based on work state identifications by a self-organizing map[J]. IEEE/ASME Transactions on Mechatronics,2004,9(3): 520-528. doi: 10.1109/TMECH.2004.836253 [24] GOPI E S,PALANISAMY P. Maximizing Gaussianity using kurtosis measurement in the kernel space for kernel linear discriminant analysis[J]. Neurocomputing,2014,144: 329-337. doi: 10.1016/j.neucom.2014.05.020 [25] SHAO Siyu,MCALEER S,YAN Ruqiang,et al. Highly accurate machine fault diagnosis using deep transfer learning[J]. IEEE Transactions on Industrial Informatics,2019,15(4): 2446-2455. doi: 10.1109/TII.2018.2864759 -