Operation reliability analysis based on fuzzy support vector machine for aircraft engines

• Autorzy: Gao J. , Wang H.

Warianty tytułu

PL

Analiza niezawodności eksploatacyjnej silników lotniczych w oparciu o metodę rozmytej maszyny wektorów nośnych (FSVM)

• Języki publikacji: EN

Abstrakty

EN

The aircraft engine is a complex and repairable system, and the diversity of its failure modes increases the difficulty of operation reliability analysis. It is necessary to establish a dynamic relationship among monitoring information, failure mode and system reliability for achieving scientific reliability analysis for aircraft engines. This paper has used fuzzy support vector machine (FVSM) method to fuse condition monitoring information. The reliability analysis models including Gamma process model and Winner process model, respectively for different failure modes, have been presented. Furthermore, these two models have been integrated on the basis of competing failures’ mechanism. Bayesian model averaging has been used to analyze the effects of different failure modes on aircraft engines’ reliability. As a result of above, the goal of an accurate analysis of the reliability for aircraft engines has been achieved. Example shows the effectiveness of the proposed model.

PL

Silnik samolotu to złożony system naprawialny, a różnorodność przyczyn jego uszkodzeń zwiększa trudność analizy niezawodności eksploatacyjnej. Istnieje konieczność ustalenia dynamicznych związków pomiędzy monitorowaniem informacji, przyczynami uszkodzeń i niezawodnością systemu, których znajomość pozwoliłaby przeprowadzać naukową analizę niezawodności silników lotniczych. Do integracji danych z monitorowania informacji, w pracy wykorzystano metodę rozmytej maszyny wektorów nośnych (FSVM). Dla różnych przyczyn uszkodzeń, przedstawiono odpowiednie modele analizy niezawodności – model procesu Gamma i model procesu Wienera. Przedstawione modele zintegrowano na podstawie mechanizmu uszkodzeń konkurujących. Do analizy wpływu różnych przyczyn uszkodzeń na niezawodność silników lotniczych wykorzystano procedurę bayesowskiego uśredniania modeli. Dzięki powyższym krokom, osiągnięto założony cel dokładnej analizy niezawodności silników samolotowych. Przykład pokazuje skuteczność proponowanego modelu.

Słowa kluczowe

EN

aircraft engine; reliability analysis; competing failure; Bayesian model averaging; data fusion

PL

silnik samolotu; analiza niezawodności; uszkodzenie konkurujące; bayesowskie uśrednianie modeli; fuzja danych

• Wydawca: Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne
• Czasopismo: Eksploatacja i Niezawodność
• Rocznik: 2015
• Tom: Vol. 17, no. 2
• Strony: 186--193
• Opis fizyczny: Bibliogr. 27 poz., rys., tab.

Twórcy

autor

Gao J.

• Department of Management Shijiazhuang Mechanical Engineering College Shijiazhuang, Hebei 050003, China

autor

Wang H.

• College of Civil Aviation Nanjing University of Aeronautics and Astronautics Nanjing, Jiangsu210016, China

Bibliografia

• 1. Bagdonavičius V, Bikelis A & Kazakevičius V et al. Analysis of joint multiple failure mode and linear degradation data with renewals. Journal of Statistical Plaaning and Inference 2007;137(7): 2191-2207, http://dx.doi.org/10.1016/j.jspi.2006.07.002.
• 2. Bedford T, Dewan I , Meileijson I. The signal model: A model for competing risks of opportunistic maintenance. European Journal of Operational Research 2011; 214(3):665-673, http://dx.doi.org/10.1016/j.ejor.2011.05.01.
• 3. Bocchetti D, Giorgio M & Guida M et al. A competing risk model for the reliability of cylinder lines in marine Diesel engines. Reliability Engineering and System Safety 2009; 94(8):1299-1307, http://dx.doi.org/10.1016/j.ress.2009.01.010.
• 4. Chen B E, Lramer J L & Greene M H. Competing risk analysis of correlated failure time data. Biometrics 2008; 64(1):172-179, http://dx.doi.org/10.1111/j.1541-0420.2007.00868.x.
• 5. Cheng M Y, Hoang N D, et al. A novel time-dependent evolutionary fuzzy SVM inference model for estimating construction project at ompletion. Engineering Application of Artificial Intelligence 2012; 25(3):744-752, http://dx.doi.org/10.1016/j.engappai.2011.09.02.
• 6. Chinnam RB. On-line reliability estimation for individual components using statistical degradation signal models. Quality and Reliability Engineering International 2002; 18(1): 53–73, http://dx.doi.org/10.1002/qre.45.
• 7. Cobel J B. Merging data sources to predict remaining useful life-An automated method to identify prognostic parameters. University of Teenessee, Knoxville 2010.
• 8. Elwany A H , Gebraeel N Z. Sensor driven prognostic models for equipment replacement and spare part s inventory. IIE Transactions 2008; 40(7) : 629-639, http://dx.doi.org/10.1080/0740817070173081.
• 9. Hong D H, Hwang C. Support vector fuzzy regression machines. Fuzzy sets and systems 2003 ; 138 (2-1):271-281.
• 10. Kenneth P. Measuring the Performance of a HUM System - the Features that Count. Proceeding of Third International Conference on Health and Usage Monitoring - HUMS2003 . Australia: DSTO Platforms Sciences Laboratory; 2003.
• 11. Kikuchi T, Abe S. Comparison between error correcting output codes and fuzzy vector machines. Pattern Recognition Letters 2005; 26(12): 1937-1945, http://dx.doi.org/10.1016/j.patrec.2005.03.014.
• 12. Kundu D& Sarhan A M. Analysis of incomplete data in presence of competing risks among several groups. IEEE Transactions on Reliability 2006 ;55(2):262 – 269, http://dx.doi.org/10.1109/TR.2006.874919.
• 13. Lehmann A. Joint modeling of degradation and failure time data. Journal of Statistical Planning and Inference 2009;139(5):1693–1706, http://dx.doi.org/10.1016/j.jspi.2008.05.02.
• 14. Li J A, Wu Y, Keung Lai K, et al. Reliability estimation and prediction of multi-state components and coherent systems. Reliability Engineering & System Safety 2005; 88(1): 93-98, http://dx.doi.org/10.1016/j.ress.2004.07.010.
• 15. Lu H, Kolarik WJ& Lu S. Real time performance reliability prediction. IEEE Transactions on Reliability 2001; 50 (4) : 353-357, http://dx.doi.org/10.1109/24.983393.
• 16. Pareek B, Kundu D, Kumar S. On progressively competing risks data for Weibull distributions. Computational ststistics and data analysis 2009; 53(12-1):4083-4094.
• 17. Park C, Kulasekera K B. Parametric inference of incomplete data with competing risks among several groups. IEEE Transactions on Reliability 2004; 53(1):11–21, http://dx.doi.org/10.1109/TR.2003.821946.
• 18. Peng H, Feng Q M, Coit D W. Reliability and maintenance modeling for systems subject to multiple dependent competing failure process. IIE Transactions 2011; 43(5):12-22.
• 19. Polpo A, Sinha D. Correction in Bayesian nonparametric estimation in a series system or a competing-risk model. Statistics and Probability Letters 2011; 81(12):1756-1759, http://dx.doi.org/10.1016/j.spl.2011.07.023.
• 20. Salinas-Torres V, Pereira C , Tiwari R. Bayesian nonparametric estimation in a series system or a competing risks model. Journal of Nonparametric Statistics 2002; 14(4):449-458, http://dx.doi.org/10.1080/10485250213114.
• 21. Sapankevych N, Sankar R. Time series prediction using support vector machines: a survey. Computation Intelligence Magazine, IEEE 2009; 4(2):24-38, http://dx.doi.org/10.1109/MCI.2009.932254.
• 22. Suarez E L, Duffy M I, Gamache R N et al. Jet engine life prediction systems integrated with prognostics health management. Proceeding of IEEE Aerospace Conference;2004.
• 23. Su C, Zhang Y. System reliability assessment based on Wiener process and competing failure analysis. Journal of Southeast University2010; 26(4):554-557.
• 24. Sugier J, AnderS gJ. Modelling and evaluation of deterioration process with maintenance activities. Eksploatacja i Niezawodnosc – Maintenance and Reliability 2013; 15 (4): 305–311.
• 25. Vapnik, V. The nature of statistical learning theory. Springer-Berlag, New York, 1995, http://dx.doi.org/10.1007/978-1-4757-2440-0.
• 26. Wang C P, Ghosh M. Bayesian analysis of bivariate competing risks model with covariates. Journal of Statistical Planning and Inference2003; 115(2-1):441-459.
• 27. Xing L D, Levitin G. Combinatorial analysis of systems with competing failures subject to failure isolation and propagation effects. Reliability Engineering and System Safety 2010 ; 95(11):1210-1215, http://dx.doi.org/10.1016/j.ress.2010.06.014.