An approach for feature extraction and selection from non-trending data for machinery prognosis

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jul 8, 2014
James Kuria Kimotho Walter Sextro

Abstract

With the paradigm shift towards prognostic and health management (PHM) of machinery, there is need for reliable PHM methodologies with narrow error bounds to allow maintenance engineers take decisive maintenance actions based on the prognostic results. Prognostics is mainly concerned with the estimation of the remaining useful life (RUL) or time to failure (TTF). The accuracy of PHM methods is usually a function of the features extracted from the raw data obtained from sensors. In cases where the extracted features do not display clear degradation trends, for instance highly loaded bearings, the accuracy of the state of the art PHM methods is significantly affected. The data which lacks clear degradation trend is referred to as non-trending data. This study
presents a method for extracting degradation trends from nontrending condition monitoring data for RUL estimation. The raw signals are first filtered using a discrete wavelet transform (DWT) denoising filter to remove noise from the acquired signals. Time domain, frequency domain and timefrequency domain features are then extracted from the filtered signals. An autoregressive (AR) model is then applied to the extracted features to identify the degradation trends. Features representing the maximum health information are then selected based on a performance evaluation criteria using extreme learning machine (ELM) algorithm. The selected features can then be used as inputs in a prognostic algorithm. The feasibility of the method is demonstrated using experimental bearing vibration data. The performance of the method is evaluated on the accuracy of RUL estimation and the results show that the method can be used to accurately estimate RUL
with a maximum error of 10%.

How to Cite

Kimotho, J. K., & Sextro, W. (2014). An approach for feature extraction and selection from non-trending data for machinery prognosis. PHM Society European Conference, 2(1). https://doi.org/10.36001/phme.2014.v2i1.1462
Abstract 836 | PDF Downloads 687

##plugins.themes.bootstrap3.article.details##

Keywords

feature extraction, Remaining useful Life, autoregressive model, ELM, feature selection, non-trending

References
Ayalew, S., Babu, M. C., & Rao, L. K. M. (2012). Comparison of new approach criteria for estimating the order of autoregressive process. IOSR Journall of Mathematics, 1(3), 10–20.
Bator, M., Dirks, A., Monks, U., & Lohweg, V. (2012). Feature extraction and reduction applied to sensorless drive diagnosis. 22. Workshop, Computational Intelligence, Dortmund, 163–178.
Benkedjouh, T., Medjaher, K., Zerhouni, N., & Rechak, S. (2013). Remaining useful life estimation based on nonlinear feature reduction and support vector machines. Engineering Application of Artificial Intelligence, 26, 1751–1760.
Camci, F., Medjaher, K., Zerhouni, N., & Nectoux, P. (2012). Feature evaluation for effective bearing prognostics. Quality and Reliability Engineering International.
Dragomir, O. E., Gouriveau, F. D., Minca, E., & Zerhouni, N. (2009). Review of prognostic problem in conditionbased maintenance. European Control Conference, ECC’09.
Galar, D., Kumar, U., & Zhao, W. (2012). Remaining useful life estimation using time trajectory tracking and support vector machines. In 25th international congress on condition monitoring and diagnostic engineering.
Georgoulas, G., Loutas, T., Stylios, C. D., & Kostopoulos. (2013). Bearing fault detection based on hybrid ensemble detector and empirical mode decomposition. Mechanical Systems and Signal Processing, 41(1-2), 510–525.
Gu, H., Zhao, J., & Zhang, X. (2013). Hybrid methodology of degradation feature extraction for bearing prognostics. Mainten ance and Reliability, 15(2), 195–201.
Huang, G.-B., Zhu, Q.-Y., & Siew, C.-K. (2006). Extreme learning machine: Theory and applications. Neurocomputing, 70, 489–501.
Junsheng, C., Dejie, Y., & Yu, Y. (2006). A fault diagnosis approach for roller bearings based on emd method and ar model. Mechanical Systems and Signal Processing, 20, 350–362.
Kim, H.-E., Tan, A. C. C., Mathew, J., & Choi, B.-K. (2012). Bearing fault prognosis based on health state probability estimation. Expert Systems with Applications, 39, 5200–5213. doi: 10.1016/j.eswa.2011.11.019
Li, B., Zhang, P.-L., Tian, H., Mi, S.-s., Liu, D.-s., & Ren, G.-q. (2011). : A new feature extraction and selection scheme for hybrid fault diagnosis of gearbox. Expert Systems with Applications, 38, 10000–10009.
Maio, F. D., Hu, J., Tse, P., Petch, M., Tsui, K., & Zio, E. (2012). Ensemble-approaches for clustering health status of oil sand pumps. Expert Systems with Applications, 39, 4847-4859.
Medjaher, K., Camci, F., & Zerhouni, N. (2012). Feature extraction and evaluation for health assessment and failure prognostics. Proceedings of First European Conference of the Prognostics and Health Management Society,.
Nectoux, P., Gouriveau, R., Medjaher, K., Ramasso, E., Morello, B., Zerhouni, N., & Varnier, C. (2012). Pronostia: An experimental platform for bearing accelerated degradation tests. IEEE International Conference on Prognostics and Health Management, Denver, CO, USA.
Ramasso, E., & Gouriveau, R. (2010). Prognostics in switching systems: Evidential markorvian classification of real-time neuro-fuzzy predictions. In Ieee international conference on prognostics and system health management, macau.
Saxena, A., & Vachtsevanos, G. (2007). Optimum feature selection and extraction for fault diagnosis and prognosis. In Proceedings of the 2007 aaai fall symposium on artificial intelligence for prognosis.
Stoica, P., Friedlander, B., & Sonderstrom, T. (1988). A high-order yule-walker method for estimation of the ar parameters of an arma model. Systems and Control Letters, 99–105.
Sugumaran, V., Muralidharan, V., & Ramachandran, K. I. (2007). Feature selection using decision tree and classification through proximal support vector machine for fault diagnostics of roller bearings. Mechanical Systems and Signal Processing, 21, 930–942.
Tran, V. T., & Yang, B.-S. (2010). Machine fault diagnosis and condition prognosis using classification and regression trees and neuro-fuzzy inference systems. Control and Cybernetics, 39, 22-54.
Wang, Z., Lu, C., Wang, Z., Liu, H., & Fan, H. (2013). Fault diagnosis and health assessment for bearings using the mahalanobis-taguchi system based on EMDSVD. Transactions of the Institute of Measurement and Control, 35(6), 798–807.
Xiong, X., & Yang, S. (2012). A new procedure for extracting fault feature of multi-frequency signal from rotating machinery. Mechanical Systems and Signal Processing, 32, 306–319.
Yu, Y., Dejie, Y., & Junsheng, C. (2006). A roller bearing fault diagnosis method based on emd energy entropy and ann. Journal of Sound and Vibration, 294, 269–277.
Zhang, K., Li, Y., Scarf, P., & Ball, A. (2011). Feature selection for high-dimensional machinery fault diagnosis data using multiple models and radial basis function networks. Neurocomputing, 74, 2941–2952.
Zhang, Y., Zuo, H., & Bai, F. (2013). Classification of fault location and performance degradation of a roller bearing. Measurement, 46, 1178–1189.
Section
Technical Papers