Andris Vaivads, Jevgēnijs Tereščenko and Vladimirs Šestakovs
The article presents a semiotic model of “aircraft conditions” in flight and multilevel structures of an aircraft. The hierarchical structure of abstract models is divided into blocks and levels that make them more compact by applying a mathematical apparatus corresponding to the goals sated. The above models were tested on the basis of statistical data on TU-154 aircraft failures for 10 years. Various aircraft functional system failures in flight were examined. The state of the aircraft is identified by normative indicators recorded in the “Aircraft Technical Operation Manual”.
Most flight delays in aviation enterprises are related to air traffic management and technical centers. This can happen for various reasons: untimely removal of defects, lack of spare parts, deficiencies in maintenance scheduling, etc. Another reason may be inefficient management in the system of preparing the aircraft for departure. The article suggests a possible option of such an assessment as well as the results obtained from the use of this methodology applied to a specific airline.
Ruta Bogdane, Aleksandrs Bitiņš, Vladimirs Šestakovs and Yasaratne Bandara Dissanayake
In this article, the authors offer a methodology for determining the quality of airline performance by taking into account the level of flight safety on the basis of factor analysis and the results of methodology approbation in the conditions of a functioning airline. The assessment of the level of airline performance quality taking into account the level of flight safety within a certain time span is rather sensitive, informative and reliable. They allow us to detect those changes in industrial and economic conditions and factors that are related to a certain degree of potential deterioration of flight safety. This creates conditions for revealing the tendencies towards the deterioration of flight safety at the stage of their origin, when they have not yet caused deep, irreversible changes in the flight safety of an airline.
The paper considers the problem of active fault diagnosis for discrete-time stochastic systems over an infinite time horizon. It is assumed that the switching between a fault-free and finitely many faulty conditions can be modelled by a finite-state Markov chain and the continuous dynamics of the observed system can be described for the fault-free and each faulty condition by non-linear non-Gaussian models with a fully observed continuous state. The design of an optimal active fault detector that generates decisions and inputs improving the quality of detection is formulated as a dynamic optimization problem. As the optimal solution obtained by dynamic programming requires solving the Bellman functional equation, approximate techniques are employed to obtain a suboptimal active fault detector.
One of the most important subsystems of the vehicles and machines operating currently in industry and transportation are the rotating subsystems. During the operation, due to the forcing factors influence, the technical state of them is changing and the failure can occur. Fault diagnosis is maintenance task considered as an essential in such subsystems, since possibility of an early detection and diagnosis of the faulty condition can save both time and money. To do this the analysis of the subsystems vibrations is performed. The identified technical state should be considered in a context of the ability and different inability states. Therefore, the first step of the diagnostic procedure is the ability and different inability states identification.
Traditional data-driven techniques of fault diagnosis require signal processing for feature extraction, as they are unable to work with raw signal data, consequently leading to need for both expert knowledge and human work. The emergence of deep learning architectures in condition-based maintenance promises to ensure high performance fault diagnosis while lowering necessity for expert knowledge and human work. This article presents authors initial research in deep learning-based data-driven fault diagnosis of rotating subsystems. The proposed technique input raw three-axis accelerometer signal as high-definition image into deep learning layers, which automatically extract signal features, enabling high classification accuracy.