Fault Diagnosis of Wheelset Bearings Using CMWPE and SaE-ELM
-
摘要: 针对DF4型内燃机车轮对轴承不同故障状态的判别问题, 提出了一种基于复合多尺度加权排列熵(Composit multiscale weighted permutation entropy, CMWPE)和自适应进化极限学习机(Self-adaptive evolutionary extreme learning machine, SaE-ELM)的机车轮对轴承故障识别方法。CMWPE基于复合粗粒化和加权排列熵的思想, 能很好地区分信号的不同模式。SaE-ELM通过自适应进化算法对极限学习机的输入权重、隐含层参数和输出权重进行优化, 解决了ELM随机选取网络参数的局限性, 提高了网络的泛化性能。计算机车轮对轴承不同健康状态下振动信号的CMWPE, 利用SaE-ELM识别轴承所属故障类型及故障程度。在机务段的JL-501轴承检测台上采集了7种不同健康状态的轮对轴承试件的振动信号数据。结果表明: CMWPE特征提取效果优于MPE和MWPE; SaE-ELM模式识别效果优于参数不经优化的ELM。所提方法能够有效诊断机车轮对轴承的不同故障, 且故障识别率达到100%。
-
关键词:
- 机车轮对轴承 /
- 故障诊断 /
- 特征提取 /
- 模式识别 /
- 复合多尺度加权排列熵 /
- 自适应进化极限学习机
Abstract: Aiming at the identification of different fault states of DF4 typed diesel locomotives, a fault diagnosis method is proposed by the combination of Composite Multiscale Weighted Permutation Entropy (CMWPE) and Self-Adaptive Evolutionary Extreme Learning Machine (SaE-ELM). CMWPE is based on the idea of composite coarsening and weighted permutation entropy, which can distinguish the different modes of signals very well. SaE-ELM optimizes the input weight, hidden layer parameter and output weight of the extreme learning machine by adaptive evolutionary algorithm, which solves the limitation of ELM random selection of network parameters and improves the generalization performance of the network. The CMWPE of vibration signals of wheelset bearings in different health states is used to identify the type and degree of fault of bearings by SaE-ELM. The vibration signal data of seven wheelset bearing specimens in different health conditions were collected on the JL-501 bearing test bench of the locomotive Depot. The results show that CMWPE feature extraction is better than MPE and MWPE, and SaE-ELM pattern recognition is better than ELM without optimized parameters. The proposed method can effectively diagnose different faults of locomotive wheelset bearings, and the fault recognition rate reaches 100%.-
Key words:
- locomotive wheelset bearing /
- fault diagnosis /
- feature extraction /
- pattern recognition /
- CMWPE /
- SaE-ELM
-
图 10 图 8中7种轮对轴承振动信号的CMWPE
表 1 机车轮对轴承故障类型及样本数量
轴承健康状态 样本数量 状态标签 正常 80 1 外圈轻度故障 80 2 外圈中度故障 80 3 滚动体轻度故障 80 4 保持架轻度故障 80 5 保持架、滚动体复合故障 80 6 内圈轻度故障 80 7 表 2 不同方法的准确率对比
方法 准确率/% CMWPE+SaE-ELM 100 CMWPE+ELM 98.57 MWPE+SaE-ELM 87.14 MPE+SaE-ELM 73.57 -
[1] ZHANG C L, LIU Y L, WAN F Y, et al. Adaptive filtering enhanced windowed correlated kurtosis for multiple faults diagnosis of locomotive bearings[J]. ISA Transactions, 2020, 101: 421-429. doi: 10.1016/j.isatra.2020.01.033 [2] WU S D, WU C W, HUMEAU-HEURTIER A. Refined scale-dependent permutation entropy to analyze systems complexity[J]. Physica A: Statistical Mechanics and its Applications, 2016, 450: 454-461. doi: 10.1016/j.physa.2016.01.044 [3] ZHANG L, XIONG G L, LIU H S, et al. Bearing fault diagnosis using multi-scale entropy and adaptive neuro-fuzzy inference[J]. Expert Systems with Applications, 2010, 37(8): 6077-6085. doi: 10.1016/j.eswa.2010.02.118 [4] ZHOU J Z, XIAO J, XIAO H, et al. Multifault diagnosis for rolling element bearings based on intrinsic mode permutation entropy and ensemble optimal extreme learning machine[J]. Advances in Mechanical Engineering, 2014, 6: 803919. doi: 10.1155/2014/803919 [5] WU S D, WU P H, WU C W, et al. Bearing fault diagnosis based on multiscale permutation entropy and support vector machine[J]. Entropy, 2012, 14(8): 1343-1356. doi: 10.3390/e14081343 [6] FADLALLAH B, CHEN B D, KEIL A, et al. Weighted-permutation entropy: a complexity measure for time series incorporating amplitude information[J]. Physical Review E, 2013, 87(2): 022911. doi: 10.1103/PhysRevE.87.022911 [7] YIN Y, SHANG P J. Weighted multiscale permutation entropy of financial time series[J]. Nonlinear Dynamics, 2014, 78(4): 2921-2939. doi: 10.1007/s11071-014-1636-2 [8] ZHENG J D, DONG Z L, PAN H Y, et al. Composite multi-scale weighted permutation entropy and extreme learning machine based intelligent fault diagnosis for rolling bearing[J]. Measurement, 2019, 143: 69-80. doi: 10.1016/j.measurement.2019.05.002 [9] 张龙, 成俊良, 杨世锡, 等. 基于时序模型和自联想神经网络的齿轮故障程度评估[J]. 振动与冲击, 2019, 38(2): 18-24.ZHANG L, CHENG J L, YANG S X, et al. Fault severity assessment for gears based on AR model and auto-associative neural network[J]. Journal of Vibration and Shock, 2019, 38(2): 18-24. (in Chinese) [10] 何园园, 张超, 朱腾飞. ELMD熵特征融合与PSO-SVM在齿轮故障诊断中的应用[J]. 机械科学与技术, 2019, 38(2): 271-276. https://www.cnki.com.cn/Article/CJFDTOTAL-JXKX201902018.htmHE Y Y, ZHANG C, ZHU T F. Application of ELMD entropy feature fusion and PSO-SVM in gear fault diagnosis[J]. Mechanical Science and Technology for Aerospace Engineering, 2019, 38(2): 271-276. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JXKX201902018.htm [11] HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1-3): 489-501. doi: 10.1016/j.neucom.2005.12.126 [12] CAO J W, LIN Z P, HUANG G B. Self-adaptive evolutionary extreme learning machine[J]. Neural Processing Letters, 2012, 36(3): 285-305. doi: 10.1007/s11063-012-9236-y [13] HUO Z Q, ZHANG Y, SHU L, et al. A new bearing fault diagnosis method based on fine-to-coarse multiscale permutation entropy, laplacian score and SVM[J]. IEEE Access, 2019, 7: 17050-17066. doi: 10.1109/ACCESS.2019.2893497 [14] 姚德臣, 杨建伟, 程晓卿, 等. 基于多尺度本征模态排列熵和SA-SVM的轴承故障诊断研究[J]. 机械工程学报, 2018, 54(9): 168-176.YAO D C, YANG J W, CHENG X Q, et al. Railway rolling bearing fault diagnosis based on muti-scale imf permutation entropy and SA-SVM classifier[J]. Journal of Mechanical Engineering, 2018, 54(9): 168-176. (in Chinese) [15] XIA J N, SHANG P J, WANG J, et al. Permutation and weighted-permutation entropy analysis for the complexity of nonlinear time series[J]. Communications in Nonlinear Science and Numerical Simulation, 2016, 31(1-3): 60-68. doi: 10.1016/j.cnsns.2015.07.011 [16] 王余奎, 李洪儒, 叶鹏. 基于多尺度排列熵的液压泵故障识别[J]. 中国机械工程, 2015, 26(4): 518-523. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGJX201504018.htmWANG Y K, LI H R, YE P. Fault identification of hydraulic pump based on multi-scale permutation entropy[J]. China Mechanical Engineering, 2015, 26(4): 518-523. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGJX201504018.htm [17] HUO Z Q, ZHANG Y, JOMBO G, et al. Adaptive multiscale weighted permutation entropy for rolling bearing fault diagnosis[J]. IEEE Access, 2020, 8: 87529-87540. doi: 10.1109/ACCESS.2020.2992935 [18] 岳忠奇, 吴涛, 顾宏. 基于SaCE-ELM的地铁牵引控制单元快速故障诊断[J]. 大连理工大学学报, 2016, 56(3): 270-278. https://www.cnki.com.cn/Article/CJFDTOTAL-DLLG201603008.htmYUE Z Q, WU T, GU H. Fast fault diagnosis of metro traction control unit based on SaCE-ELM[J]. Journal of Dalian University of Technology, 2016, 56(3): 270-278. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DLLG201603008.htm [19] SHABANLOU S. Improvement of extreme learning machine using self-adaptive evolutionary algorithm for estimating discharge capacity of sharp-crested weirs located on the end of circular channels[J]. Flow Measurement and Instrumentation, 2018, 59: 63-71. https://www.sciencedirect.com/science/article/pii/S0955598617301942 [20] TANG X F, CHEN L. A self-adaptive evolutionary weighted extreme learning machine for binary imbalance learning[J]. Progress in Artificial Intelligence, 2018, 7(2): 95-118.