Abstract
Targeting the non-stationary characteristics of diesel engine vibration signals and the limitations of singular value decomposition (SVD) technique, a new method based on improved local mean decomposition (LMD), SVD technique and relevance vector machine (RVM) was proposed for the identification of diesel valve fault in this study. Firstly, the vibration signals were acquired through the vibration sensors installed on the cylinder head in one normal state and four fault states of valve trains. Secondly, an improved LMD method was used to decompose the non-stationary signals into a set of stationary product functions (PF), from which the initial feature vector matrices can be formed automatically. Then, the singular values were obtained by applying the SVD technique to the initial feature vector matrixes. Finally, slant binary tree and sort separability criterion were combined to determine the structure of multi-class RVM, and the singular values were regarded as the fault feature vectors of RVM in the identification of fault types of diesel valve clearance. The experimental results showed that the proposed fault diagnosis method can effectively extract the features of diesel valve clearance and identify the diesel valve fault accurately.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Shang B L, Xia Y, Zhang Z R et al. Fault diagnosis of diesel valve by using GAalgorithm[J]. Transactions of CSICE, 2000, 18(4): 419–422(in Chinese).
Wang C D, Zhang Y Y, Zhong Z Y. Fault diagnosis for diesel valve trains based on time-frequency images[J]. Mechanical Systems and Signal Processing, 2008, 22(8): 1981–1993.
Jiang Y H, Tang B P, Qin Y et al. Feature extraction method of wind turbine based on adaptive Morlet wavelet and SVD[J]. Renewable Energy, 2011, 36(8): 2146–2153.
Cheng J S, Yu D J, Tang J S et al. Application of SVM and SVD technique based on EMD to the fault diagnosis of the rotating machinery[J]. Shock and Vibration, 2009, 16(1): 89–98.
Hong H, Wang X L, Tao Z Y et al. Centroid-based sifting for empirical mode decomposition[J]. Journal of Zhejiang University-Science C: Computers & Electronics, 2011, 12(2): 88–95.
Yang Y, Cheng J S, Zhang K. An ensemble local mean decomposition method and its application to local rubimpact fault diagnosis of the rotor systems[J]. Measurement, 2012, 45(3): 561–570.
Smith J S. The local mean decomposition and its application to EEG perception data[J]. Journal of the Royal Society Interface, 2005, 2(5): 443–454.
Park C, Looney D, Hulle M M. The complex local mean decomposition[J]. Neurocomputing, 2011, 74(6): 867–875.
Chen B J, He Z J, Chen X F et al. A demodulating approach based on local mean decomposition and its applications in mechanical fault diagnosis[J]. Measurement Science & Technology, 2011, 22(5): 55704–55716.
Zhang J H, Liu Y. Bearing fault diagnosis based on improved LMD[C]. In: Proceedings of the 2011 International Conference on Transportation and Mechanical & Electrical Engineering. Changchun, China, 2011. 2544–2547.
Sorsa T, Koivo H N. Application of artificial neural networks in process fault diagnosis[J]. Automatica, 1993, 29(4): 843–849.
Lee T L, Lin H M, Lu Y P. Assessment of highway slope failure using neural networks[J]. Journal of Zhejiang University-Science A: Applied Physics & Engineering, 2009, 10(1): 101–108.
Huang J, Hu X G, Geng X. An intelligent fault diagnosis method of high voltage circuit breaker based on improved EMD energy entropy and multi-class support vector machine[J]. Electric Power Systems Research, 2011, 81(2): 400–407.
Vapnik V N. An overview of statistical learning theory[J]. IEEE Transactions on Neural Networks, 1999, 10(5): 988–999.
Yan Z G, Wang Z Z, Ren X M. Joint application of feature extraction based on EMD-AR strategy and multi-class classifier based on LS-SVM in EMG motion classification[J]. Journal of Zhejiang University -Science A: Applied Physics & Engineering, 2007, 8(8): 1246–1255.
Tipping M E. Sparse Bayesian learning and the relevance vector machine[J]. Journal of Machine Learning Research, 2001, 1(3): 211–244.
Widodo A, Kim E Y, Son J D. Fault diagnosis of low speed bearing based on relevance vector machine and support vector machine[J]. Expert Systems with Applications, 2009, 36(3): 7252–7261.
Ren D Q. Study on Methods and System for Fault Characteristics Extraction of Rotating Machines Based on Local Mean Decomposition[D]. Zhejiang University, Hangzhou, China, 2008(in Chinese).
Rilling G, Flandrin P, Goncalves P. On empirical made decomposition and its algorithms[C]. In: Proceedings of IEEE EURASIP Workshop on Nonlinear Signal and Image Processing. Grado, Italy, 2003.
Zhao X Z, Ye B Y. Selection of effective singular values using difference spectrum and its application to fault diagnosis of headstock[J]. Mechanical Systems and Signal Processing, 2011, 25(5): 1617–1631.
Wang X D, Ye M Y. Classification of data from electronic nose using relevance vector machines[J]. Sensors and Actuators B: Chemical, 2009, 140(1): 143–148.
Takahashi F, Abe S. Decision-tree-based multiclass support vector machines[C]. In: The 9th International Conference on Neural Information Processing. Singapore, 2002. 1418–1422.
Author information
Authors and Affiliations
Corresponding author
Additional information
Supported by the National High Technology Research and Development Program of China (“863” Program, No. 2014AA041501).
Liu Yu, born in 1987, male, doctorate student.
Rights and permissions
About this article
Cite this article
Liu, Y., Zhang, J., Lin, J. et al. Application of improved LMD, SVD technique and RVM to fault diagnosis of diesel valve trains. Trans. Tianjin Univ. 21, 304–311 (2015). https://doi.org/10.1007/s12209-015-2430-z
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12209-015-2430-z