Remaining Useful Life Prediction of High-speed Railway Traction System Based on Performance Degradation

ZHU Kaiqiang; LU Ningyun; JIANG Bin

doi:10.13976/j.cnki.xk.2020.9365

Volume 49 Issue 3

Jun. 2020

Turn off MathJax

Article Contents

Abstract

References

INFORMATION AND CONTROL > 2020 > 49(3): 335-342. > DOI: 10.13976/j.cnki.xk.2020.9365 CSTR: 32166.14.xk.2020.9365

ZHU Kaiqiang, LU Ningyun, JIANG Bin. Remaining Useful Life Prediction of High-speed Railway Traction System Based on Performance Degradation[J]. INFORMATION AND CONTROL, 2020, 49(3): 335-342. DOI: 10.13976/j.cnki.xk.2020.9365

Citation:

PDF (1629 KB)

Remaining Useful Life Prediction of High-speed Railway Traction System Based on Performance Degradation

College of Automation Engineering, Nanjing University of Aeronautics & Astronautics, Nanjing 210016, China

More Information

Received Date: July 03, 2019
Revised Date: March 27, 2020
Accepted Date: September 03, 2019
Available Online: December 01, 2022
Published Date: June 19, 2020

Graphical Abstract

Abstract

Abstract

To address the problems of complex structures, complicated performance degradation parameters, and missing failure threshold, we propose a remaining useful life (RUL) prediction method based on performance degradation. First, we extract various statistical features of degraded parameters, and perform feature selection using monotonic, related, and redundancy indexes to reduce the interference of redundant and irrelevant features. We propose a health-based strategy that assesses the system failure condition by assessing the health of the system to predict RUL without a failure threshold. Then, we use the selected features to train long- and short-term memory networks for degraded trajectory prediction. We conduct a case study using a hardware-in-the-loop simulation platform for the traction system of Chinese railway high-speed trains to predict the RUL of the DC-link circuit with capacitance degradation. Experimental results show the validity and superiority of the proposed method.
- RUL prediction,
- feature extraction,
- health assessment,
- LSTM network

FullText(HTML)

References (23)

References

[1]	张曙光. CRH2型动车组[M].北京:中国铁道出版社, 2008. Zhang S G. CRH2 electric multiple unit[M]. Beijing:China Railway Publishing House, 2008.
[2]	Lu X S, Li Y F, Wu M L, et al, Rail temperature rise characteristics caused by linear eddy current break if high-speed train[J]. Journal of Traffic and Transportation Engineering(English Edition), 2014, 1(6):448-456. doi: 10.1016/S2095-7564(15)30295-6
[3]	张妍, 王村松, 陆宁云, 等.基于退化特征相似性的航空发动机寿命预测[J].系统工程与电子技术, 2019, 41(16):1414-1421. http://d.old.wanfangdata.com.cn/Periodical/xtgcydzjs201906033 Zhang Y, Wang C S, Lu N Y, et al, Remaining useful life prediction for aero-engine based on the similarity of degradation characteristics[J]. Systems Engineering and Electronics, 2019, 41(16):1414-1421. http://d.old.wanfangdata.com.cn/Periodical/xtgcydzjs201906033
[4]	胡昌华, 施权, 司小胜, 等.数据驱动的寿命预测和健康管理技术研究进展[J].信息与控制, 2017, 46(1):72-82. http://ic.sia.cn/CN/abstract/abstract12500.shtml Hu C H, Shi Q, Si X S, et al. Data-driven life prediction and health management:State of the art[J]. Information and Control, 2017, 46(1):72-82. http://ic.sia.cn/CN/abstract/abstract12500.shtml
[5]	Ungurean L, Carstoiu L, Micea M V, et al. Battery state of health estimation:A structured review of models, methods and commercial devices[J]. International Journal of Energy Research, 2016, 41:151-181. http://cn.bing.com/academic/profile?id=f25e0103eed67e0430db75c8e7476818&encoded=0&v=paper_preview&mkt=zh-cn
[6]	彭宇, 刘大同.数据驱动故障预测和健康管理综述[J].仪器仪表学报, 2014, 35(3):481-495. http://d.old.wanfangdata.com.cn/Periodical/yqyb201403001 Peng Y, Liu D T. Data-driven prognostics and health management:A review of recent adcances[J]. Journal of Instrumentation, 2014, 35(3):481-495. http://d.old.wanfangdata.com.cn/Periodical/yqyb201403001
[7]	Liao L X, Kottig F. Review of hybrid prognostics approaches for remaining useful life prediction of engineered systems, and an application to battery life prediction[J]. IEEE Transactions on Reliability, 2014, 63(1):191-207. doi: 10.1109/TR.2014.2299152
[8]	Khelif R, Chebel-Morello B, Malinowski S, et al. Direct remaining useful life estimation based on support vector regression[J]. IEEE Transactions on Industrial Electronics, 2017, 64(3):2276-2285. doi: 10.1109/TIE.2016.2623260
[9]	Wang C S, Lu N Y, Wang S L, et al. Dynamic long short-term memory neural-network-based indirect remaining-useful-life prognosis for satellite lithium-ion battery[J]. Applied Sciences, 2018, 8(11):2078. doi: 10.3390/app8112078
[10]	Ordone C, Lasheras F S, Pardoinas J R, et al. A hybrid ARIMA-SVM model for the study of the remaining useful life of aircraft engines[J]. Journal of Computational and Applied Mathematics, 2019, 346:184-191. doi: 10.1016/j.cam.2018.07.008
[11]	邓超, 陶志奎, 吴军, 等.基于性能退化的数控机床剩余寿命预测[J].机械工程学报, 2018, 54(17):181-189. http://d.old.wanfangdata.com.cn/Periodical/jxgcxb201817024 Deng C, Tao Z K, Wu J, et al. Residual life prediction for NC machine tool based on performance degradation[J]. Journal of Mechanical Engineering, 2018, 54(17):181-189. http://d.old.wanfangdata.com.cn/Periodical/jxgcxb201817024
[12]	Ordonez C, Lashera F S, Pardinas J R, et al. A hybrid ARIMA-SVM model for the study of the remaining useful life of aircraft engines[J]. Journal of Computational and Applied Mathematics, 2019, 346:184-191. doi: 10.1016/j.cam.2018.07.008
[13]	Zhong S S, Xie X L, Lin L. Two-layer random forests model for case reuse in case-based reasoning[J]. Expert Systems with Applications, 2015, 42(24):9412-9425. doi: 10.1016/j.eswa.2015.08.005
[14]	Guo L, Li N P, Jia F, et al. A recurrent neural network based health indicator for remaining useful life prediction of bearings[J]. Neurocomputing, 2017, 240:98-109. doi: 10.1016/j.neucom.2017.02.045
[15]	Ramasso E, Rombaut M, Zerhouni N. Joint prediction of continuous and discrete states in time-series based on belief functions[J]. IEEE Transactions on Cybernetics, 2013, 43(1):37-50. doi: 10.1109/TSMCB.2012.2198882
[16]	Zhang C Y, Lu N Y, Wang C S, et al. An RBMs-BN method to RUL prediction of traction converter of CRH2 trains[J]. Engineering Application of Atrificial Intelligence, 2019, 85:46-56. doi: 10.1016/j.engappai.2019.06.001
[17]	赵文清, 朱永利, 张小奇.应用支持向量机的变压器故障组合预测[J].中国电机工程学报, 2008, 28(25):14-19. http://d.old.wanfangdata.com.cn/Periodical/zgdjgcxb200825003 Zhao W Q, Zhu Y L, Zhan X Q. Combinational forecast for transformer faults based on support vector machine[J]. Proceeding of CSEE, 2008, 28(25):17-19. http://d.old.wanfangdata.com.cn/Periodical/zgdjgcxb200825003
[18]	孙博, 赵宇, 黄伟, 等.电子产品健康监测和故障预测方法的案例研究[J].系统工程与电子技术, 2007, 29(6):1012-1016. doi: 10.3321/j.issn:1001-506X.2007.06.042 Sun B, Zhao Y, Huang W, et al. Case study of prognostic and health management methodology for electronics[J]. Systems Engineering and Electronics, 2007, 29(6):1012-1016. doi: 10.3321/j.issn:1001-506X.2007.06.042
[19]	Yang C, Yang C, Peng T, et al. A fault-injection strategy for traction drive control systems[J]. IEEE Transactions on Industrial Electronics, 2017, 64(7):5719-5726 doi: 10.1109/TIE.2017.2674610
[20]	Lei Y G, Li N P, Gontarz S, et al. A model-based method for remaining useful life prediction of machinery[J]. IEEE Transaction on Reliability, 2016, 65(3):1314-1326. doi: 10.1109/TR.2016.2570568
[21]	Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780. doi: 10.1162/neco.1997.9.8.1735
[22]	V. Vapnik, The nature of statistical learning theory[M], Berlin, Germany:Springer, 1998.
[23]	Chen K Y, Chen L S, Chen M C, et al. Using SVM based method for equipment fault detection in a thermal power plant[J]. Computers in Industry, 2011, 62(1):42-50. doi: 10.1016/j.compind.2010.05.013