time series trending; nonlinear filtering; anomaly detection
Abstract :
[en] Gas-path measurements used to assess the health condition of an engine are corrupted by
noise. Generally, a data cleaning step occurs before proceeding with fault detection and
isolation. Classical linear filters such as the EWMA filter are traditionally used for noise
removal. Unfortunately, these low-pass filters distort trend shifts indicative of faults,
which increases the detection delay. The present paper investigates two new approaches
to nonlinear filtering of time series. On the one hand, the synthesis approach reconstructs
the signal as a combination of elementary signals chosen from a predefined library. On
the other hand, the analysis approach imposes a constraint on the shape of the signal
(e.g., piecewise constant). Both approaches incorporate prior information about the signal
in a different way, but they lead to trend filters that are very capable at noise removal
while preserving at the same time sharp edges in the signal. This is highlighted through
the comparison with a classical linear filter on a batch of synthetic data representative of
typical engine fault profiles.
Disciplines :
Space science, astronomy & astrophysics
Author, co-author :
Borguet, Sébastien ; Université de Liège - ULiège > Département d'aérospatiale et mécanique > Turbomachines et propulsion aérospatiale
Léonard, Olivier ; Université de Liège - ULiège > Département d'aérospatiale et mécanique > Turbomachines et propulsion aérospatiale
Dewallef, Pierre ; Université de Liège - ULiège > Département d'aérospatiale et mécanique > Systèmes de conversion d'énergie pour un dévelop.durable
Language :
English
Title :
Analysis versus synthesis for trending gas-path measurement time series
Publication date :
February 2015
Journal title :
Journal of Engineering for Gas Turbines and Power
ISSN :
0742-4795
eISSN :
1528-8919
Publisher :
American Society of Mechanical Engineers, New York, United States - New York
Rajamani, R., Wang, J., and Jeong, K. Y., 2004, "Condition-Based Maintenance for Aircraft Engines," ASME Paper No. GT2004-54127.
Volponi, A. J., 2003, "Foundation of Gas Path Analysis (Part I and II)," (von Karman Institute Lecture Series, number 01 in Gas Turbine Condition Monitoring and Fault Diagnosis), von Karman Institute, Rhode-St-Genese, Belgium.
Ganguli, R., 2002, "Data Rectification and Detection of Trend Shifts in Jet Engine Path Measurements Using Median Filters and Fuzzy Logic," ASME J. Eng. Gas Turbines Power, 124 (4), pp. 809-816.
DePold, H., and Gass, F., 1999, "The Application of Expert Systems and Neural Networks to Gas Turbine Prognostics and Diagnostics," ASME J. Eng. Gas Turbines Power, 121 (4), pp. 607-612.
Simon, D. L., Bird, J., Davison, C., Volponi, A. J., and Iverson, R. E., 2008, "Benchmarking Gas Path Diagnostic Methods: A Public Approach," ASME Paper No. GT2008-51360.
Verbist, M., Visser, W., and van Buijtenen, J. P., 2013, "Experience With Gas- Path Analysis for On-Wing Turbofan Condition Monitoring," ASME Paper No. GT2013-95739.
Shumway, R., and Stoffer, D., 2010, Time Series Analysis and Its Applications (Springer Texts in Statistics), 3rd ed., Springer, New York.
Harvey, A., and Trimbur, T., 2008, "Trend Estimation and the Hodrick-Prescott Filter," J. Jpn Stat. Soc., 38 (1), pp. 41-49.
Baillie, R., and Chung, S.-K., 2002, "Modeling and Forecasting From Trend- Stationary Long Memory Models With Applications to Climatology," Int. J. Forecasting, 18 (2), pp. 215-226.
Chen, A., and Elsayed, E., 2002, "Design and Performance Analysis of the Exponentially Weighted Moving Average Mean Estimate for Processes Subject to Random Step Changes," Technometrics, 44 (4), pp. 1-11.
Ganguli, R., and Dan, B., 2004, "Trend Shift Detection in Jet Engine Gas Path Measurements Sing Cascaded Recursive Median Filter With Gradient and Laplacian Edge Detector," ASME J. Eng. Gas Turbines Power, 126 (1), pp. 55-61.
Surrender, V., and Ganguli, R., 2005, "Adaptive Myriad Filter for Improved Gas Turbine Condition Monitoring Using Transient Data," ASME J. Eng. Gas Turbines Power, 127 (2), pp. 329-339.
Uday, P., and Ganguli, R., 2010, "Jet Engine Health Signal Denoising Using Optimally Weighted Recursive Median Filter," ASME J. Eng. Gas Turbines Power, 132 (4), p. 041601.
Elad, M., Milanfar, P., and Rubinstein, R., 2007, "Analysis Versus Synthesis in Signal Priors," Inverse Probl., 23 (3), pp. 947-968.
Borguet, S., and Léonard, O., 2010, "A Sparse Estimation Approach to Fault Isolation," ASME J. Eng. Gas Turbines Power, 132 (2), p. 021601.
Borguet, S., and Léonard, O., 2011, "Constrained Sparse Estimation for Improved Fault Isolation," ASME J. Eng. Gas Turbines Power, 133 (12), p. 121602.
Gustafsson, F., 2000, Adaptive Filtering and Change Detection,Wiley, New York.
Kim, S.-J., Koh, K., Boyd, S., and Gorinevsky, D., 2009, "'1 Trend Filtering," SIAM Rev., 51 (2), pp. 339-360.
Tibshirani, R., and Taylor, J., 2011, "The Solution Path of the Generalized Lasso," Ann. Stat., 39 (3), pp. 1335-1371.
Fuchs, J. J., 2004, "On Sparse Representations in Arbitrary Redundant Basis," IEEE Trans. Inf. Theory, 50 (6), pp. 1341-1344.
Chen, S., Donoho, D., and Saunders, M., 1998, "Atomic Decomposition by Basis Pursuit," SIAM J. Sci. Comput., 20 (1), pp. 33-61.
Malioutov, D., Cetin, M., and Willsky, A., 2005, "A Sparse Signal Reconstruction Perspective for Source Localization With Sensor Arrays," IEEE Trans. Signal Process., 53 (8), pp. 3010-3022.
Fuchs, J. J., 2004, "Recovery of Exact Sparse Representations in the Presence of Noise," IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '04), Montreal, Canada, May 17-21, pp. 533-536.
Fletcher, R., 2000, Practical Methods of Optimization, Wiley, New York.
Simon, D. L., 2010, "Propulsion Diagnostic Method Evaluation Strategy (Pro- DIMES) User's Guide," NASA Glenn Research Center, Cleveland, OH, Technical Memorandum TM-2010-215840.
Meszaros, C., 1996, "Fast Cholesky Factorization for Interior Point Methods of Linear Programming," Comput. Math. Appl., 31 (4, 5), pp. 49-54.
Gorinevsky, D., 2008, "Efficient Filtering Using Monotonic Walk Model," IEEE American Control Conference, Seattle, WA, June 11-13, pp. 2816-2821.
Borguet, S., and Léonard, O., 2008, "A Sensor-Fault-Tolerant Diagnosis Tool Based on a Quadratic Programming Approach," ASME J. Eng. Gas Turbines Power, 130 (2), p. 021605.