A Residual Variance Based Discriminant Function and its Algorithm

Abstract:

Time series analysis is advantageous since it offers insight into the underlying dynamics and forecasts system behavior. The construction of the discriminant function is of vital importance in the time series analysis based fault diagnosis. Aiming at the problem that some of the time series analysis based fault diagnosis methods exist the weakness of higher time complexity, weaker discriminant ability and insufficient online diagnosis power, this paper proposes an approach which makes full use of the characteristics of the model and observation data to construct the discriminant function, and presents an efficient algorithm which can effectively recognize the system state by the proposed discriminant function. As compared to the related work, it has the characteristics of lower time complexity, shorter computation time and stronger distinguished ability, without the requirement of same orders of the reference model and the detected model. The fault diagnosis steps based on the proposed discriminant function and its algorithm are also suggested.

• Periodical: Applied Mechanics and Materials (Volumes 738-739)
• Pages: 354-360
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.738-739.354
• Online since: March 2015
• Authors: Jian Jun Zhang, Ye Xin Song, Yong Qu
• Keywords: Autoregressive Model, Discriminant Function, Fault Diagnosis, Residual Variance, Time Complexity, Time Series Analysis

References

[1] Isermann, R., Model-based Fault-detection and Diagnosis-Status and Applications, Annual Reviews in Control, 2005, 29(1): 71-85.

DOI: 10.1016/j.arcontrol.2004.12.002

[2] Isermann, R., Diagnosis methods for electronic controlled vehicles, Vehicle System Dynamics, 2001, 36(2), (3): 77-177.

DOI: 10.1076/vesd.36.2.77.3554

[3] Dron, J., Rasolofondraibe, L., Couet, C., and Pavan, A., Fault Detection and Monitoring of a Ball Bearing Benchtest and a Production Machine via Autoregressive Spectrum Analysis, Journal of Sound and Vibration, 1998, 218(3): 501-525.

DOI: 10.1006/jsvi.1998.1837

[4] Bettocchi, R., and Spina, P., ARX Linear Model Set-up for Fault Diagnosis of Gas Turbine Sensors, proceedings of the 1997 International Gas Turbine & Aeroengine Congress & Exposition, 97-GT-27, Orlando, FL, June (1997).

DOI: 10.1115/97-gt-027

[5] Apley, D., and Shi, J., GLRT for Statistical Process Control of Autocoelated Proces, IIE Transactions, 1999, 31(12): 1123-1134.

DOI: 10.1080/07408179908969913

[6] Riemer, P., Mitchell, J., and Beckman, W., The Use of Time Series Analysis in Fault Detection and Diagnosis Methodologies, ASHRAE Transactions, 2002, 108(2): 384-394.

[7] Chen, S., Ray, A., and Rajagopalan, V., Symbolic Time Series Analysis for Anomaly Detection: A Comparative Evalution, Signal Processing, 2005, 85(9): 1859-1868.

DOI: 10.1016/j.sigpro.2005.03.014

[8] Gluch, J., and Krzyzanowski, J., New Attempt for Diagnostics of the Geometry eterioration of the Power System Based on Thermal Measurement, proceedings of GT2006 ASME Turbo Expo: Power for Land, Sea and Air, 2006(2): 531-53.

DOI: 10.1115/gt2006-90263

[9] Gorinevsky, D., Monotonic Regression Filters for Trending Deterioration Faults, proceedings of the 2004 American Control Conference, 2004(6): 5394-5399.

DOI: 10.23919/acc.2004.1384710

[10] Brockwell, P., and Davis, R., Introduction to Time Series and Forecasting, Springer-Verlag: New York, (2002).