98. Locomotive drive system fault diagnosis based on dynamic self-adaptive blind source separation

Bin Ren1, Rujiang Hao2, Shaopu Yang3

Shijiazhuang Tiedao University, Hebei, China

1Corresponding author

E-mail: 1renbin@stdu.edu.cn, 2haorj@stdu.edu.cn, 3yangsp@stdu.edu.cn

Received 29 May 2016; received in revised form 1 July 2016; accepted 13 July 2016

DOI https://doi.org/10.21595/jme.2016.17350

Abstract. Drive system is one of most important key equipment to guarantee safe and stable operation in locomotive. With time variation, unpredictability and nonstationary, fault source of drive system is not obtained by traditional fault diagnosis method. Blind source separation is a kind of method on source signals separation under transmission channel unknown instance. The method of Blind source separation based on variable metric empirical mode decomposition is proposed. Intrinsic mode function is built, redundancy factors are reduced, and recurrent neural network is used to adaptive blind separation. The method is verified by data analysis of on‑line measuring. The results show that separation efficiency is improved and unaffected with iteration time in the process of fault information separation, which will be better for further fundamental research and provide technique support for the locomotive.

Keywords: drive system, adaptive blind separation, fault diagnosis, locomotive running gear.


[1]        Chen Xuefeng, Li Jimeng, Cheng Hang, et al. Research and application of condition monitoring and fault diagnosis technology in wind turbines. Journal of Mechanical Engineering, Vol. 47, Issue 9, 2011, p. 45‑52.

[2]        Shi Xizhi Blind Signal Processing Theory and Practice. Shanghai Jiao Tong University Press, Shanghai, 2008.

[3]        Chen Ximing, Huang Shuoyi Blind source separation: problem, principle and method. Electronic Information Warfare Technology, Vol. 23, Issue 2, 2008, p. 1‑5.

[4]        Li Yi, He Yongyong, Li Zhinong, et al. Study on application of blind source separation and wavelet de-noising in rubbing fault acoustic signal analysis. Journal of Mechanical Strength, Vol. 27, Issue 6, 2006, p. 719‑724.

[5]        Fabrizio G., Farina A. An adaptive filtering algorithm for blind waveform estimation in diffuse multipath channels. IET Radar Sonar, Vol. 5, Issue 3, 2011, p. 322‑330.

[6]        Zhang Jie Blind source separation of non-stationary signals based on adaptive maximum signal‑to‑noise ratio method. Journal of Southwest Jiaotong University, Vol. 48, Issue 4, 2013, p. 769‑775.

[7]        Wu Wenfeng, Chen Xiaohu, Su Xunjia Blind source separation of single-channel mechanical signal based on empirical mode decomposition. Journal of Mechanical Engineering, Vol. 47, Issue 4, 2011, p. 12‑16.

[8]        Delvecchio S., Antoni J. Extraction of angle deterministic signals in the presence of stationary speed fluctuations with cyclostationary blind source separation. Mechanical Systems and Signal Processing, Vol. 27, 2012, p. 350‑61.

[9]        Bonnardot F., Randall R. B., Guillet F. Extraction of second-order cyclostationary sources application to vibration analysis. Mechanical Systems and Signal Processing, Vol. 19, Issue 6, 2005, p. 1230‑44.

[10]     Clark F. S. P., Petragla M. R., Haddad D. B. A new initialization method for frequency-domain blind source separation algorithms. Signal Processing Letters, Vol. 18, Issue 6, 2011, p. 343‑346.

[11]     Nguyen V. H., Rutten C., Golinval J.-C. Fault diagnosis in industrial systems based on blind source separation techniques using one single vibration sensor. Shock and Vibration, Vol. 19, Issue 5, 2012, p. 795‑801.

[12]     Tse P. W., Zhang J. Y., Wang X. J. Blind source separation and blind equalization algorithms for mechanical signal separation and identification. Journal of Vibration and Control, Vol. 12, Issue 4, 2006, p. 395‑423.

[13]     Hattay Jamel, Belaid Samir, Naanaa Wady Non-negative matrix factorisation for blind source separation in wavelet transform domain. IET Signal Processing, Vol. 9, Issue 2, 2015, p. 111‑119.

[14]     Inan Huseyin A., Erdogan Alper T. Convolutive bounded component analysis algorithms for independent and dependent source separation. IEEE Transactions on Neural Networks and Learning Systems, Vol. 26, Issue 4, 2015, p. 697‑708.

[15]     Li Zong, Feng Zhipeng, Chu Fulei A performance index of blind source separation based on improved crosstalk index. Journal of Vibration and Shock, Vol. 31, Issue 18, 2012, p. 83‑88.

[16]     Shen Yongjun, Yang Shaopu, Kong Deshun New method of blind source separation in under-determined mixtures based on singular value decomposition and application. Journal of Mechanical Engineering, Vol. 45, Issue 8, 2009, p. 64‑70.

[17]     Yang Xiaokuo, Wang Shuzhao, Wang Jun, et al. Method for detection of multi-frequency weak signal based on vector blind source separation. Chinese Journal of Sensors and Actuators, Vol. 21, Issue 8, 2008, p. 1393‑1397.

[18]     Li Xuexia, Feng Jiuchao A blind separation method for chaotic signals. Physica Sinica, Vol. 56, Issue 2, 2007, p. 701‑706.

[19]     Zhang Jie, Gao Hongli, Chen Chunjun, et al. Blind source separation method and application for nonstationary vibration signal of high speed train. Journal of Mechanical Engineering, Vol. 50, Issue 19, 2014, p. 97‑104.

[20]     Chen Hao, Bai Lin, Zhou Zhiyu Discussion about development and application of blind source separation technology. Space Electronic Technology, 2013, p. 1‑6.

[21]     Liu Ju, Nie Kaibao, He Zhenya On separability and separating method of nonlinear mixed signals. Journal of Electronics and Information Technology, Vol. 25, Issue 1, 2003, p. 54‑61.

Cite this article

Ren Bin, Hao Rujiang, Yang Shaopu Locomotive drive system fault diagnosis based on dynamic self‑adaptive blind source separation. Journal of Measurements in Engineering, Vol. 4, Issue 3, 2016, p. 140‑147.


Journal of Measurements in Engineering. September 2016, Volume 4, Issue 3

JVE International Ltd. ISSN Print 2335-2124, ISSN Online 2424-4635, Kaunas, Lithuania