Evaluation of Features with Changing Effectiveness for Prognostics



Vepa Atamuradov Fatih Camci


Feature evaluation is crucial to identify the best features and to achieve high accuracy in diagnostics and prognostics. Feature evaluation for prognostics is a developing research area with several publications in recent years. Most, if not all, of existing methods to evaluate features for prognostics base on the feature changes in the whole life of the system under observation. In other words, feature values collected throughout the failure degradation are analyzed to create a goodness value for the feature. In reality, the goodness of the features may change during the failure progression. A feature may be good representative of failure progression in the initial phase but not in the final phases, or vice versa. This paper presents dynamic nature of representation capabilities of features throughout the failure degradation and proposes a novel approach to evaluate the features considering their dynamic nature. Proposed approach involves feature segmentation based on their representation capabilities and feature fusion utilizing the segmented evaluations. The presented approach has been applied in simulated and real degradation datasets. Real degradation dataset were obtained from accelerated aging tests of Li-ion batteries in the lab environment. The results from both datasets show that dynamic feature evaluation improves SoH estimation accuracy.

How to Cite

Atamuradov, V., & Camci, F. (2016). Evaluation of Features with Changing Effectiveness for Prognostics. Annual Conference of the PHM Society, 8(1). https://doi.org/10.36001/phmconf.2016.v8i1.2573
Abstract 18 | PDF Downloads 11



prognostics, Feature evaluation

Camci, F. et al., 2013. Feature Evaluation for Effective Bearing Prognostics. Quality and Reliability Engineering International, 29(4), pp.477–486. Available at: http://doi.wiley.com/10.1002/qre.1396.
Camci, F. & Chinnam, R.B., 2005. Dynamic Bayesian networks for machine diagnostics: Hierarchical Hidden Markov models vs. competitive learning. Proceedings of the International Joint Conference on Neural Networks, 3, pp.1752–1757.
Chan, K. & Fu, W. “Efficient time series matching by wavelets”, Proceedings of the the IEEE International Conference on Data Engineering, 1999.
Cecille, F., Dana, K. & B;, O., 2015. An evaluation of classifier-specific filter measure performance for feature selection. PATTERN RECOGNITION, 48(5), pp.1812–1826.
Guana, D. et al., 2014. A Review of Ensemble Learning Based Feature Selection. IETE Technical Review, 31(3), pp.190–198.
Hannah Inbarani, H., Bagyamathi, M. & T;, A.A., 2015. A novel hybrid feature selection method based on rough set and improved harmony search. Neural Computing and Applications, 26(8), pp.1859–1880.
Honeine, P., 2012. Online Kernel Principal Component Analysis: A Reduced-Order Model. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 34(9), pp.1814–1826.
Javed, K. et al., 2015. Enabling Health Monitoring Approach Based on Vibration Data for Accurate Prognostics. IEEE Transactions on Industrial Electronics, 62(c), pp.647–656. Available at: http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6824783.
Koegh, E., Chu, S., Hart, D. and Pazzani, M. “Segmenting Time Series: A Survey and Novel Approach”, Data Mining in Time Series Databases, Singapore: World Scientific Publishing Co., pp. 1-21, 2004.
Lamraoui, M. et al., 2015. Chatter detection in milling machines by neural network classification and feature selection. Journal of Vibration and Control, 21(7), pp.1251–1266.
Linxia, L., 2014. Discovering Prognostic Features Using Genetic Programming in Remaining Useful Life Prediction. Industrial Electronics, IEEE Transactions on, 61(5), pp.2464–2472.
Lui, K., Gabraeel, N. Z., Shi, J. “A data-level fusioin model for developing composite health indices for degradation modeling and prognostics analysis”, Automation Science and Engineering, IEEE Transactions, 10(3), 652-664, 2013.
Liu, L. et al., 2015. Entropy-based sensor selection for condition monitoring and prognostics of aircraft engine. Microelectronics Reliability, 55(9-10), pp.2092–2096. Available at: http://linkinghub.elsevier.com/retrieve/pii/S0026271415001687.
Lui, J., Zhang, M., Zuo, H., Xie, J. “Remaining useful life prognostics for aeroengine based on superstatistics and information fusion”, Chinese Journal of Aeronoutics, 1086-1096, 2014.
Mwangi, B., Tian, T.V. & Soares, J.C., 214AD. A Review of Feature Reduction Techniques in Neuroimaging. Neuroinformatics, 12(2), pp.229–244.
Nui, G., Yang, B. S. “Intelligent condition monitoring and prognostics system based on data-fusion strategy”, Expert Systems with Applications, 37(2), 8831-8840, 2010.
Peng, Y.. et al., 2015. Locality structure preserving based feature selection for prognostics. Intelligent Data Analysis, 19(3), pp.659–682.
Tianzhen, W., Hao, X. & Jingang, H., 2015. Cascaded H-Bridge Multilevel Inverter System Fault Diagnosis Using a PCA and Multiclass Relevance Vector Machine Approach. IEEE TRANSACTIONS ON POWER ELECTRONICS, 30(12), pp.7006–7018.
Wang, L. et al., 2014. Global and Local Structure Preservation for Feature Selection. IEEE transactions on neural networks and learning systems, 25(6), pp.1083–1095. Available at: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6657801.
Z, W., Jin, C. & Guangming, D., 2011. Constrained independent component analysis and its application to machine fault diagnosis. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 25(7), pp.2501–2512.
Zhang, J. & Lee, J., 2011. A review on prognostics and health monitoring of Li-ion battery. Journal of Power Sources, 196(15), pp.6007–6014. Available at: http://linkinghub.elsevier.com/retrieve/pii/S0378775311007865 [Accessed December 15, 2013].
Technical Papers