基于多域融合CNN的高速列车转向架故障检测

doi:10.16182/j.issn1004731x.joss.201811053

系统仿真学报 ›› 2018, Vol. 30 ›› Issue (11): 4492-4497.doi: 10.16182/j.issn1004731x.joss.201811053

• 短文 • 上一篇

基于多域融合CNN的高速列车转向架故障检测

吴昀璞, 金炜东, 黄颖坤

西南交通大学电气工程学院,四川成都 610031

收稿日期:2018-05-25 修回日期:2018-07-12 发布日期:2019-01-04
作者简介:吴昀璞(1991-),男,江苏,博士生,研究方向为故障诊断,贝叶斯深度学习等;金炜东(1959-),男,安徽,博士,教授,博导,研究方向为智能信息处理,系统仿真与优化方法等。

Fault Diagnosis of High Speed Train Bogie Based on Multi-domain Fusion CNN

Wu Yunpu, Jin Weidong, Huang Yingkun

School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China

Received:2018-05-25 Revised:2018-07-12 Published:2019-01-04

摘要/Abstract

摘要： 高速列车转向架在服役运行中发生构件的性能退化和各类故障会严重威胁到列车的运行安全。针对高速列车振动信号的高复杂度、高耦合和强非线性,提出一种基于多域融合卷积神经网络的转向架故障检测方法,对于时域信号进行噪声注入以增强噪声鲁棒性与模型泛化性能,使用内嵌时频变换层获取信号时频表示信息,对于获得的多域多通道信息,利用卷积神经网络的固有特性实现自适应权重特征融合。实验结果表明,提出的方法提高了高速列车转向架故障诊断的准确率,同时具有较强的噪声鲁棒性与工况适应性。

关键词: 高速列车转向架, 故障诊断, 多域融合, 卷积神经网络

Abstract: The performance degradation and failures of high-speed train bogie components directly threaten the operation security of train. A fault detection method based on multi-domain fusion convolutional neural network is proposed to address the high complexity, high coupling and strong nonlinearity of vibration signals. Noise injection for time domain signal is used to enhance noise robustness and generalization of the model. Signal time-frequency representation information is obtained through embedded time-frequency transformation layer. Adaptive weight-based fusion is implemented through intrinsic characteristics of the convolutional neural network to handle the multi-domain multi-channel information. The experimental results show that the proposed method improves the accuracy of fault diagnosis of high-speed train bogies with good noise robustness and adaptability to work condition.

Key words: high speed train bogie, fault diagnosis, multi-domain fusion, convolutional neural network

中图分类号:

TP277

吴昀璞, 金炜东, 黄颖坤. 基于多域融合CNN的高速列车转向架故障检测[J]. 系统仿真学报, 2018, 30(11): 4492-4497.

Wu Yunpu, Jin Weidong, Huang Yingkun. Fault Diagnosis of High Speed Train Bogie Based on Multi-domain Fusion CNN[J]. Journal of System Simulation, 2018, 30(11): 4492-4497.

参考文献

[1] Lu Y, Xiang P, Dong P, et al.Analysis of the effects of vibration modes on fatigue damage in high-speed train bogie frames[J]. Engineering Failure Analysis (S1350-6307), 2018, 89: 222-241.
[2] Iglesias E L, Thompson D J, Smith M, et al.Anechoic wind tunnel tests on high-speed train bogie aerodynamic noise[J]. International Journal of Rail Transportation (S2324-8378), 2017, 5(2): 87-109.
[3] Qin N, Jin W D, Huang J, et al. High Speed Train Bogie Fault Signal Analysis Based on Wavelet Entropy Feature[J]. Advanced Materials Research (S1662-8985), 2013, 753/754/755: 2286-2289.
[4] Wu Z, Jin W, Qin N.Fault feature analysis of high-speed train suspension system based on multivariate multi-scale sample entropy[C]//2016 35th Chinese Control Conference (CCC), 2016: 3913-3918.
[5] Du J, Jin W, Cai Z, et al.A New Feature Evaluation Algorithm and Its Application to Fault of High-Speed Railway[C]//Proceedings of the Second International Conference on Intelligent Transportation. Springer, Singapore, 2016: 1-14.
[6] Lecun Y, Bengio Y, Hinton G.Deep learning[J]. Nature (S1476-4687), 2015, 521(7553): 436-444.
[7] Jia F, Lei Y, Lin J, et al. Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data[J]. Mechanical Systems and Signal Processing (S0888-3270), 2016, 72/73(Supplement C): 303-315.
[8] Janssens O, Slavkovikj V, Vervisch B, et al.Convolutional Neural Network Based Fault Detection for Rotating Machinery[J]. Journal of Sound and Vibration (S0022-460X), 2016, 377(Supplement C): 331-345.
[9] Karim F, Majumdar S, Darabi H, et al.LSTM fully convolutional networks for time series classification[J]. IEEE Access (S2169-3536), 2018, 6: 1662-1669.
[10] Chen Z, Li W.Multisensor Feature Fusion for Bearing Fault Diagnosis Using Sparse Autoencoder and Deep Belief Network[J]. IEEE Transactions on Instrumentation and Measurement (S0018-9456), 2017, 66(7): 1693-1702.
[11] Jing L, Wang T, Zhao M, et al.An Adaptive Multi-Sensor Data Fusion Method Based on Deep Convolutional Neural Networks for Fault Diagnosis of Planetary Gearbox[J]. Sensors (S1424-8220), 2017, 17(2): 414-415.
[12] Hu H, Tang B, Gong X, et al.Intelligent Fault Diagnosis of the High-Speed Train With Big Data Based on Deep Neural Networks[J]. IEEE Transactions on Industrial Informatics (S1551-3203), 2017, 13(4): 2106-2116.
[13] Zhao Y, Guo Z H, Yan J M.Vibration signal analysis and fault diagnosis of bogies of the high-speed train based on deep neural networks[J]. Journal of Vibroengineering (S2538-8460), 2017, 19(4): 2456-2474.
[14] Noh H, You T, Mun J, et al.Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization[G]//Guyon I, Luxburg U V, Bengio S, et al. Advances in Neural Information Processing Systems 30. Curran Associates, Inc., 2017: 5109-5118.
[15] Kingma D P, Welling M. Auto-encoding variational bayes [J]. arXiv preprint (S2331-8422) arXiv:1312.6114, 2013.
[16] Zheng Y.Methodologies for Cross-Domain Data Fusion: An Overview[J]. IEEE Transactions on Big Data (S2332-7790), 2015, 1(1): 16-34.
[17] Stutz D.Understanding convolutional neural networks [R]. InSeminar Report, Fakultät für Mathematik, Informatik und Naturwissenschaften Lehr-und Forschungsgebiet Informatik VIII Computer Vision, 2014.
[18] 鞠萍华. 旋转机械早期故障特征提取的时频分析方法研究[D]. 重庆: 重庆大学, 2010.
Ju Pinghua.Research on the Time-frequency Analysis Method to Extract Early Fault Features of Rotating Machinery[D]. Chongqing: Chongqing University, 2010.

基于多域融合CNN的高速列车转向架故障检测

Fault Diagnosis of High Speed Train Bogie Based on Multi-domain Fusion CNN

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张立峰, 王会忍. 基于卷积神经网络及有限元仿真的电容层析成像图像重建[J]. 系统仿真学报, 2022, 34(4): 712-718.
[2]	敖邦乾, 杨莎, 令狐金卿, 叶振环. 基于级联神经网络疲劳驾驶检测系统设计[J]. 系统仿真学报, 2022, 34(2): 323-333.
[3]	祝志超, 吴定会, 岳远昌. 基于监督核熵成分分析的发动机磨损故障诊断[J]. 系统仿真学报, 2022, 34(1): 45-52.
[4]	李元, 耿泽伟. 基于LLE与K均值聚类算法的工业过程故障诊断[J]. 系统仿真学报, 2021, 33(9): 2066-2073.
[5]	王印松, 孙天舒. 基于二分类NMF网络的执行器故障状态评估[J]. 系统仿真学报, 2021, 33(8): 1882-1891.
[6]	吴曦, 马骏. 虚实共生复杂体系仿真实验支撑技术研究[J]. 系统仿真学报, 2021, 33(7): 1722-1728.
[7]	位晶晶, 刘勤明, 叶春明, 李冠林. 基于GA-SVR的小样本数据缺失下的设备故障诊断[J]. 系统仿真学报, 2021, 33(6): 1342-1349.
[8]	赵瑛, 陆耀, 张健, 梁启弟, 龙炜. 基于深度神经网络的多视角人体动作识别[J]. 系统仿真学报, 2021, 33(5): 1019-1030.
[9]	吴定会, 祝志超, 韩欣宏. 基于BO-SDAE多源信号的风电机组轴承故障诊断[J]. 系统仿真学报, 2021, 33(5): 1148-1156.
[10]	仝卫国, 庞雪纯, 朱赓宏. 基于卷积神经网络的气液两相流流型识别方法[J]. 系统仿真学报, 2021, 33(4): 883-891.
[11]	马榕, 陈秋瑞, 张晗, 梅铮, 王锐, 魏伟. 基于单目深度估计的低功耗视觉里程计[J]. 系统仿真学报, 2021, 33(12): 3001-3011.
[12]	黄欣, 方钰, 顾梦丹. 基于卷积神经网络的X线胸片疾病分类研究[J]. 系统仿真学报, 2020, 32(6): 1188-1194.
[13]	李炜, 周丙相, 蒋栋年. 基于深度学习序贯检验的电源车故障诊断方法[J]. 系统仿真学报, 2020, 32(4): 638-648.
[14]	樊名鲁, 王艳, 纪志成. 基于特征生成的轴承不均衡数据故障诊断[J]. 系统仿真学报, 2020, 32(12): 2438-2448.
[15]	王红军, 黎邹邹, 邹湘军. 基于Adaboost与CNN的木材表面缺陷检测[J]. 系统仿真学报, 2019, 31(8): 1636-1645.