A Data-Driven Neural Network Approach for Remaining Useful Life Prediction

Ji Hong Yan; Chao Zhong Guo; Xing Wang; De Bin Zhao

doi:10.4028/www.scientific.net/KEM.450.544

Paper Titles

Work Assignment Optimization Using Genetic Algorithms
p.526

A Female Glasses Fitting Model Based on Neural Network
p.530

An Integrated Fuzzy Multi-Attribute Decision-Making Methodology for Evaluation of Mechanical Product
p.534

Genetic Algorithm Based Methodology for Optimal Maintenance Scheduling of Multi-Unit Systems
p.539

A Data-Driven Neural Network Approach for Remaining Useful Life Prediction
p.544

Sliding Mode Control with Fuzzy Tuning to Pneumatic Driving 6-DOF Parallel Robot
p.548

Wavelet Filter Approach for GPS Attitude Tracking System on Ship
p.552

Structural Optimization Using Multi Evolutionary System Co-Exist Genetic Algorithm
p.556

Dynamic Sub-Population Genetic Algorithm Combined with Dynamic Penalty Function to Solve Constrained Optimization Problems
p.560

HomeKey Engineering MaterialsKey Engineering Materials Vol. 450A Data-Driven Neural Network Approach for...

A Data-Driven Neural Network Approach for Remaining Useful Life Prediction

Abstract:

This paper proposed a neural network (NN) based remaining useful life (RUL) prediction approach. A new performance degradation index is designed using multi-feature fusion techniques to represent deterioration severities of facilities. Based on this indicator, back propagation neural networks are trained for RUL prediction, and average of the networks’ outputs is considered as the final RUL in order to overcome prediction errors caused by random initiations of NNs. Finally, an experiment is set up based on a Bently-RK4 rotor unbalance test bed to validate the neural network based life prediction models, experimental results illustrate the effectiveness of the methodology.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Key Engineering Materials (Volume 450)

Pages:

544-547

DOI:

https://doi.org/10.4028/www.scientific.net/KEM.450.544

Citation:

Cite this paper

Online since:

November 2010

Authors:

Ji Hong Yan, Chao Zhong Guo, Xing Wang, De Bin Zhao

Keywords:

BP Neural Network (BPNN), Data-Driven Method, Prediction, Prognostics, Remaining Useful Life

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] A. K. S. Jardine, D. Lin, D. Banjevic, A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mechanical System and Signal Processing, 20(2006)1483-1510.

DOI: 10.1016/j.ymssp.2005.09.012

Google Scholar

[2] T. Ghidini, C. Donne, Fatigue life prediction using fracture mechanics methods. Engineering Fracture Mechanics, 75(2009)134-148.

DOI: 10.1016/j.engfracmech.2008.07.008

Google Scholar

[3] C. Y. Yin, H. Lu et al., A Prognostic Assessment Method for Power Electronics Modules. 2nd Electronics System Integration Technology Conference, (2008), pp.1353-1358.

DOI: 10.1109/estc.2008.4684552

Google Scholar

[4] R. Huang, L. Xi, X. Li et al., Residual life predictions for ball bearings based on self-organizing map and back propagation neuralnetwork methods. Mechanical Systems and Signal Processing, 21(2007)193-207.

DOI: 10.1016/j.ymssp.2005.11.008

Google Scholar

[5] F. Li, C. Liu, Application Study of BP Neural Network on Stock Market Prediction. Ninth International Conference on Hybrid Intelligent Systems, (2009), pp.174-177. Degradation cycle Performance indicator Degradation cycle RUL.

DOI: 10.1109/his.2009.248

Google Scholar