Remaining Useful Life Prediction Model Based on Gradient Feature Stochastic Filtering

Lei Sun; Gang Li; Gang Li

doi:10.4028/www.scientific.net/AMM.380-384.1151

Paper Titles

Research on the Web Mining Algorithm Application in Tourism E-Commerce
p.1133

A Method for Computing Flight Track in Simulation and Reconstruction
p.1137

The Best Perturbation Method for the Parameter Inversion of Two-Dimension Convection-Diffusion Equation
p.1143

The Principle and Implementation of Novel FRC Algorithm
p.1147

Remaining Useful Life Prediction Model Based on Gradient Feature Stochastic Filtering
p.1151

Transient Source Two-Dimensional Source Item Inverse Problem Research and Accuracy Impact Analysis Based on the Differential Evolution Algorithm in the Wide/Shallow Watercourse
p.1156

A Study on Airborne Munition Trajectory Simulation Ontology
p.1161

Adaptive Genetic Algorithm for Multilayer RBF Network and its Application on Real Function Approximation
p.1166

Research on Route Planning of Cruise Missile Based on Improved Particle Swarm Optimization Algorithm
p.1170

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 380-384Remaining Useful Life Prediction Model Based on...

Remaining Useful Life Prediction Model Based on Gradient Feature Stochastic Filtering

Abstract:

This paper proposed a remaining useful life prediction model to avoid the original monitoring information due to the influence of the oil monitoring linear regression process, thereby reducing the prediction error. According to the process of equipment wear, we analyzed the impact of the relationship between the wear, the metal particle concentration and the remaining useful life; then established an improved filter model. Using maximum likelihood parameter to estimate model parameters. Finally, taking a certain type of self-propelled Gun Engine Oil Spectrum Data for example, and the results show that the remaining useful life prediction model of equipment has a certain practical value.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 380-384)

Pages:

1151-1155

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.380-384.1151

Citation:

Cite this paper

Online since:

August 2013

Authors:

Lei Sun, Gang Li, Gang Li

Keywords:

Gradient Feature, Remaining Useful Life, Stochastic Filtering Model

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Andrew Jardine. Optimizing Condition Based Maintenance Decisions[C]. Annual Reliability and Maintainability Symposium. 2002: 90-97.

DOI: 10.1109/rams.2002.981625

Google Scholar

[2] Matthew J. Carr, Wenbin Wang. An approximate algorithm for prognostic modelling using condition monitoring information. European Journal of Operational Research 211, 2011: 90-96.

DOI: 10.1016/j.ejor.2010.10.023

Google Scholar

[3] W Wang, B Hussin. Plant residual time modelling based on observed variables in oil samples[J]. Journal of the Operational Research Society. 2009, 60, 789-796.

DOI: 10.1057/palgrave.jors.2602621

Google Scholar

[4] Wang W and Zhang W. A model to predict the residual life of aircraft engines based on oil analysis data. 2005, Nav Log Res 52: 276–284.

DOI: 10.1002/nav.20072

Google Scholar

[5] Daming Lin, Murray Wiseman et. al. An approach to signal processing and condition-based maintenance for gearboxes subject to tooth failure [J]. Mechanical Systems and Signal Processing. 2004(18): 993-1007.

DOI: 10.1016/j.ymssp.2003.10.005

Google Scholar

[6] Yimin Zhan, V. Makis, A.K.S. Jardine. Adaptive state detection of gearboxes under varying load conditions based on parametric modeling [J]. Mechnical Systems and Signal Processing. 2004, 10: 188-221.

DOI: 10.1016/j.ymssp.2004.08.004

Google Scholar

[7] Wang W and Zhang W. A model to predict the residual life of aircraft engines based on oil analysis data. 2005, Nav Log Res 52: 276–284.

DOI: 10.1002/nav.20072

Google Scholar

[8] S.S. Wilks, Mathematical statistics, Wiley, New York, (1962).

Google Scholar

[9] Anbang Xu, Xin Jin, Ping Guo. KICA Feature Extraction in Application to FNN Based Image Registration[C]. 2006 International Joint Conference on Neural Networks. Canada July 16-21, 2006: 3602-3608.

DOI: 10.1109/ijcnn.2006.247371

Google Scholar