地铁车辆电动塞拉门的剩余寿命预测

摘要/Abstract

摘要： 针对地铁车辆客室电动塞拉门传动装置润滑不良的问题，提出了基于自组织映射（SOM）神经网络、隐马尔可夫链（HMC）模型和蒙特卡罗（MC）仿真的剩余使用寿命预测方法。该方法首先对采集到的电机电流信号进行特征提取；然后利用SOM对提取出的多维特征数据进行融合与编码，将所得结果作为HMC的输入向量，训练得到全部寿命下劣化状态转移矩阵；最后利用MC方法实现对其劣化过程的剩余使用寿命预测。故障模拟实验结果表明，该方法可以在考虑润滑不良故障模式下，有效预测得到电动塞拉门丝杆的剩余使用寿命。

关键词: 电动塞拉门, 润滑不良, 剩余使用寿命预测, 隐马尔可夫链模型, 自组织映射神经网络, 蒙特卡罗仿真

Abstract: To solve the problems of poor lubrication associated with elecrical sliding plug doors of metro vehicles, a prediction model of the remaining useful life was proposed herein based on self-organizing feature map(SOM), hidden Markov chain(HMC) and Monte Carlo(MC) simulation. Firstly, the motor current signals were collected and the features were extracted. Secondly, the SOM method was used to achieve data fusion and encoding for the multi-dimensional feature data. Then the results were used as input vector of the HMC in order to obtain state transition probabilities for the whole life. Finally, the MC simulation was used to predict the remaining useful life of the degradation process. The fault simulation experimental results show that the method can predict the remaining useful life effectively of the electrical sliding plug door with the consideration of the failure mode of poor lubrication.

Key words: electrical sliding plug door, poor lubrication, remaining useful life prediction, hidden Markov chain, self-organizing feature map neural network, Monte Carlo simulation

中图分类号:

TH17
TP18

王凌, 陈长骏, 潘静, 许宏, 陈锡爱, 那文波. 地铁车辆电动塞拉门的剩余寿命预测[J]. 中国机械工程.

Wang Ling, Chen Changjun, Pan Jing, Xu Hong, Chen Xiai, Na Wenbo. Prediction of Remaining Useful Life for Electrical Sliding Plug Door of Metro Vehicles[J]. China Mechanical Engineering.

参考文献

[1]王振东.机械润滑故障分析与预防[J].露天采矿技术, 2003(5):31-32.

Wang Zhendong.Failure Analysis and Prevention of Mechanical Lubrication[J].Opencast Mining Technology,2003(5):31-32.

[2]潘忆宁，夏军，邢宗义，等.地铁车辆车门系统的FMECA分析研究[J].轨道交通装备与技术, 2013(5)：16-19.

Pan Yining，Xia Jun，Xing Zongyi，et al. FMECA Analysis of Door System for Metro Vehicles[J].Rail Transportation Equipment and Technology, 2013(5):16-19.

[3]杨江天，赵明元，张志强，等. 基于定子电流小波包分析的牵引电机轴承故障诊断[J]. 铁道学报，2013,35(2)：32-36.

Yang Jiangtian, Zhao Mingyuan, Zhang Zhiqiang, et al.Traction Motor Bearing Fault Detection via Wavelet Packet Analysis of Stator Currents[J].Journal of the China Railway,2013,35(2):32-36.

[4]Langone R, Alzate C, Ketelaere B D,et al.LS-SVM Based Spectral Clustering and Regression for Predicting Maintenance of Industrial Machines[J]. Engineering Applications of Artificial Intelligence,2015,37(37):268-278.

[5]何群，李磊，江国乾，等.基于PCA和多变量极限学习机的轴承剩余使用寿命预测[J].中国机械工程, 2014,25(7):984-989.

He Qun, Li Lei, Jiang Guoqian, et al.Residual Life Predictions for Bearings Based on PCA and MELM[J]. China Mechanical Engineering,2014,25(7):984-989.

[6]赵洪山, 胡庆春, 李志为.基于统计过程控制的风机齿轮箱故障预测[J].电力系统保护与控制,2012,40(13): 67-73.

Zhao Hongshan, Hu Qingchun, Li Zhiwei.Failure Prediction of Wind Turbine Gearbox Based on Statistical Process Control[J].Power System Protection and Control,2012,40(13):67-73.

[7]Dong Shaojiang, Yin Shirong, Tang Baoping,et al.Bearing Degradation Process Prediction Based on the Support Vector Machine and Markov Model[J].Shock and Vibration, 2014,2014(1/2):1-15.

[8]Niu W, Cheng J, Wang G Q,et al.Fast Fault Prediction Model Based on Rough Sets and Grey Model[J]. Journal of Computational and Theotetical Nanoscience, 2013,10(6): 1460-1464.

[9]孟宗，闫晓丽，王亚超.基于LMD和HMM的旋转机械故障诊断[J].中国机械工程, 2014,25(21):2942-2946.

Meng Zong, Yan Xiaoli, Wang Yachao.Rotating Machinery Fault Diagnosis Based on Local Mean Decomposition and Hidden Markov Model[J].China Mechanical Engineering, 2014,25(21):2942-2946.

[10]蒋永华，程光明，阚君武，等. 基于NGA优化SVM的滚动轴承故障诊断[J].仪器仪表学报,2013,34(12): 2684-2689.

Jiang Yonghua，Cheng Guangming, Kan Junwu，et al. Rolling Bearing Fault Diagnosis Based on NGA Optimized SVM[J].Chinese Journal of Scientific Instrument,2013,34(12):2684-2689.

[11]申弢，黄树红，韩守木，等.基于SOFM网络的机械设备多类型信息融合与状态识别[J].机械工程学报,2001,37(1): 37-41.

Shen Tao, Huang Shuhong, Han Shoumu, et al. Multi Type Information Fusion and State Identification of Mechanical Equipment Based on SOFM Network[J]. Journal of Mechanical Engineering,2001,37(1):37-41.

[12]吴军，邵新宇，邓超. 隐马尔科夫链模型在装备运行可靠性预测中的应用[J].中国机械工程, 2010,21(19): 2345-2349.

Wu Jun, Shao Xingyu, Deng Chao.A HMC-based Equipment Operation Reliability Prediction with Multiple Observation Sequences[J]. China Mechanical Engineering,2010,21(19):2345-2349.

[13]Gebraeel N, Elwany A, Pan Jing.Residual Life Predictions in the Absence of Prior Degraduation Knowledge[J]. IEEE Trans. on Reliability,2009,58(1): 106-117.

[14]Eker O F, Camci F, Guclu A,et al.A Simple State-based Prognostic Model for Railway Turnout System[J].IEEE Trans. Industrial Electronics, 2011,58(5):1718-1726.

[15]Szaxena A, Celaya J, Saha A, et al.Metrics for Offline Evaluation of Prognostic Performance[J]. Prognostics and Health Mange, 2010,1(1):2153-2648.