Evaluation of the effectiveness of the forecasting system for special cases in flight based on the analysis of diagnostic data of the aircraft technological equipment

DOI: 10.31673/2412-9070.2020.041821

Abstract

The paper proposes an approach to assessing the effectiveness of the forecasting system for special cases in flight based on the analysis of diagnostic data of the aircraft technological equipment. Prediction of special cases in flight is the main task of parametric diagnostics of aircraft technological equipment. To solve this problem, on-board automated monitoring, diagnostics and control of onboard equipment, unloading and information support of the crew make it possible to measure a large number of parameters of the aircraft technological equipment and obtain arrays of such information in digital form. It is proposed to process the received information using the method of predicting special cases in flight based on the identification of abnormal sequences in the diagnostic data of the aircraft technological equipment. To identify anomalous sequences, it is proposed to use a hybrid stochastic model based on the combination of Markov and production models that use temporal rules to refine the transition probabilities between process states. Due to the inclusion of refining production rules in the model, the probability of describing random processes that are not Markovian increases, and it also becomes possible to integrate a priori expert knowledge into the model, which is very important for predicting special cases in flight. It is proposed to evaluate the effectiveness of the forecasting system by two criteria: the efficiency and reliability of the decisions made by the aircraft crew. In the robot, a simulation was carried out on the simulator of a winding ship A-320 for evaluating the situation as well as taking decisions from the negative inheritance of particular types of problems in the country.

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

References
1. Chandola V., Arindam Banerjee, Vipin Kumar. Anomaly detection: a survey // ACM Computing Surveys. 2009. P. 1–72.
2. Joshi M. V., Agarwal R. C., Kumar V. Predicting rare classes: can boosting make any weak learner strong? // 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., Japkowicz N., Kotcz A. Editorial: special issue on learning from imbalanced data sets // SIGKDD Explorations 6 (1). 2004. P. 1–6.
4. Steinwart I., Hush D., Scovel C. A classification framework for anomaly detection // Journal of Machine Learning Research 6. 2005. P. 211–232.
5. Tajbakhsh A., Mohammad Rahmati, Abdolreza Mirzaei. Intrusion detection using fuzzy association rules // Applied Soft Computing 9 (2). 2009. P. 462–469.
6. Xu X., Wang X. N. Adaptive network intrusion detection method based on PCA and support vector machines // ADMA 2005, Lecture Notes in Artificial Intelligence, LNAI 3584. 2005. P. 696–703.
7. Jha S., Tan K., Maxion R. Markov chains, classifiers, and intrusion detection // Proceedings of the Computer Security Foundations Workshop (CSFW). 2001, June.
8. Obidin D. The concept of functional stability for complex intellectual control systems // Zbornik prispevkov z medzinárodného vedeckého seminára «Riadenie bezpečnosti zložitẏch systémov». 18–22 februára 2013. Liptovský Mikuláš: Akadémia ozbrojených sil generála Milana Rastislava Štefánika, 2013. Str.