A method for detecting abnormal sequences in the diagnostic data of technological equipment of an aircraft to prevent special cases in flight

DOI:10.31673/2412-4338.2020.023326

Authors

  • І. О. Падалка, (Padalka I. O.) Flight Academy of the National Aviation University, Kropyvnytskyi
  • П. В. Опенько, (Open’ko P. V.) Ivan Cherniakhovskyi National Defense University of Ukraine, Kyiv
  • В. М. Руденко, (Rudenko V. M.) Donbass State Engineering Academy, Kramatorsk
  • М. П. Столяренко, (Stolyarenko M. P.) Research Center for Missile Troops and Artillery, Sumy

Abstract

Prediction of special cases in flight is the main task of parametric diagnostics of aircraft technological equipment. To solve this problem, on-board means of automated control, diagnostics and control of on-board equipment, unloading and information support of the crew use mathematical models based on the trend analysis of some registered operating time parameters. However, existing diagnostic models based on the corresponding mathematical models do not always allow predicting the occurrence of process equipment failures. What makes the task of forecasting special cases in flight relevant. The paper proposes a method for predicting special cases in flight based on identifying abnormal sequences in the diagnostic data of aircraft technological equipment. To identify abnormal sequences, it is proposed to use a hybrid stochastic model based on a combination of Markov and production models using temporal rules to specify transition probabilities between process states. By including more precise production rules in the model, the probability of describing random processes that are not Markovian is increased, and it becomes possible to integrate a priori expert knowledge into the model, which is very important for predicting special cases in flight. The application of the proposed method will allow to implement the prognostic principle of flight safety management, as well as to obtain the economic effect of preventing aircraft downtime due to sudden equipment failure.

Keywords: flight safety, special cases in flight, parametric diagnostics, forecasting, abnormal sequence, time series, temporal pattern.

References
1. Chandola, V. Anomaly detection: a survey / V. Chandola, Arindam Banerjee, Vipin Kumar // ACM Computing Surveys. – 2009. – P. 1–72.
2. Joshi, M.V. Predicting rare classes: can boosting make any weak learner strong? / M.V. Joshi, R.C. Agarwal, V. Kumar // Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining ACM. – New York, NY, USA, 2002. – P. 297–306.
3. Chawla, N.V. Editorial: special issue on learning from imbalanced data sets / N.V. Chawla, N. Japkowicz, A. Kotcz // SIGKDD Explorations 6 (1). – 2004. – P. 1–6.
4. Steinwart, I. A classification framework for anomaly detection / I. Steinwart, D. Hush, C. Scovel // Journal of Machine Learning Research 6. – 2005. – P. 211–232.
5. Tajbakhsh, A. Intrusion detection using fuzzy association rules / A. Tajbakhsh, Mohammad Rahmati, Abdolreza Mirzaei // Applied Soft Computing 9 (2). – 2009. – P. 462–469.
6. Xu, X. Adaptive network intrusion detection method based on PCA and support vector machines / X. Xu, X.N. Wang // ADMA 2005, Lecture Notes in Artificial Intelligence, LNAI 3584. – 2005. – P. 696– 703.
7. Jha, S. Markov chains, classifiers, and intrusion detection / S. Jha, K. Tan, R. Maxion // Proceedings of the Computer Security Foundations Workshop (CSFW). – 2001, June.
8. Specification based anomaly detection: a new approach for detecting network intrusions / R. Sekar, A. Gupta, J. Frullo, T. Shanbhag, A. Tiwari, H. Yang, S. Zhou // Proceedings of the 9th ACM Conference on Computer and Communications Security, ACM Press. – 2002. – P. 265–274.
9. Shah, H. Fuzzy clustering for intrusion detection / H. Shah, J. Undercoffer, A. Joshi // Proceedings of the 12th IEEE International Conference on Fuzzy Systems. – 2003. – P. 1274–1278.
10. Mahoney, M. Learning nonstationary models of normal network traffic for detecting novel attacks / M. Mahoney, P. Chan // Proceedings of 8th International Conference on Knowledge Discovery and Data Mining. – 2002. – P. 376–385.
11. Forrest, F. Using genetic algorithms to explore pattern recognition in the immune system / F. Forrest, В. Javornik, A.S. Perelson // Evol. – 1993. – Vol. 1. – № 3. – P. 191–211.
12. Self-nonself discrimination in a computer / Ф. Forrest 5, A.S. Perelson, L. Allen, R. Cherukuri // Proceedings of IEEE symposium on research in security and privacy. – Oakland, CA. – 16–18 May 1994. – P. 202–212.
13. Yeung, D.Y. Host-based intrusion detection using dynamic and static behavioral models / D.Y. Yeung, Y.X. Ding // Pattern Recognition 36. – 2003. – P. 229–243.
14. Hybrid stochastic model for detecting special types of patterns in temporal data / S.M. Kovalev, A.N. Guda, M.A. Butakova // Vestnik Rostovskogo gosudarstvennogo universiteta putey soobshcheniya. – 2013. – №3(51). – S. 36-42.
15. Ma, J. Time-series novelty detection using one-class support vector machines / J. Ma, S. Perkins // Proceedings of the International Joint Conference on Neural Networks. – July 2003. – Vol. 3. – pp. 1741–1745.

Downloads

Published

2021-04-03

Issue

No. 2 (2020)

Section

Articles