CLASSIFICATION OF NEURAL NETWORK FOR TECHNICAL CONDITION OF TURBOFAN ENGINES BASED ON HYBRID ALGORITHM

Authors

  • Valentin Potapov National Aviation University

DOI:

https://doi.org/10.18372/2306-1472.69.11057

Keywords:

artificial intelligence, air-gas channel, bypass turbofan engine, diagnostics, neural network

Abstract

Purpose: This work presents a method of diagnosing the technical condition of turbofan engines using hybrid neural network algorithm based on software developed for the analysis of data obtained in the aircraft life. Methods: allows the engine diagnostics with deep recognition to the structural assembly in the presence of single structural damage components of the engine running and the multifaceted damage. Results: of the optimization of neural network structure to solve the problems of evaluating technical state of the bypass turbofan engine, when used with genetic algorithms.

Author Biography

Valentin Potapov, National Aviation University

Graduate student.

National Aviation University, Kyiv, Ukraine.

Education: National Aviation University, Kyiv, Ukraine.

Research area: diagnostics of gas turbine engines.

References

Panin V.V., Voznyuk A.P., Popov A.V., Sun Gaoyong (2005) Influence of gas turbine engine gar-air channel operational factors and damageability on its components. Proceedings of NAU. №2. P. 49-52.

Kulyk M. (2013) Method of formulating input parameters of neural network for diagnosing gas-turbine engines . M. Kulyk, S. Dmutriev, А. Popov, A. Yakushenko. Aviation – Vilnius: Technika, – №17(2). P. 52–56.

Korotka, L.I. (2012) Improving the efficiency of computational methods for modeling the behavior of constructions are the precipitated corrosion. Dis. of candidate of technical sciences: 01.05.02 . L.I. Ko¬rotka. Dnepr, 144 p.

Kuo J.-T., Wang Y.-Y., Lung W.-S. (2006) A hybrid neural-genetic algorithm for reservoir water quality management. Water Res.Apr. Vol. 40, no. 7. Pp. 1367-1376.

Saemi M., Ahmadi M., Varjani A. Y. (2007) Design of neural networks using genetic algorithm for the permeability estimation of the reservoir. Journal of Petroleum Science and Engineering. 2007. Vol. 59. Pp. 97-105.

Lotfi, E. (2014) A novel single neuron perceptron with universal approximation and XOR computation properties. E. Lotfi, M.-R. Akbar¬zadeh-T. Computational Intelligence and Neuroscience. Vol. 2014. P. 1–6.

Goldberg D.E., Lingle R. (1985) Alleles, Loci, and the Traveling Salesman Problem, Proceedings of the First International Conference on Genetic Algorithms and Their Application , pp. 154-159.

Wang L. (2005) A hybrid genetic algorithm-neural network strategy for simulation optimization. Applied Mathematics and Computation. Vol. 170. Pp. 1329-1343.

Morimoto Т., Ouchi Y., Shimizu M., Baloch M. S.(2007) Dynamic optimization of watering Satsuma mandarin using neural networks and genetic algorithms. Water Management. Vol. 93. Pp. 1-10.

Rutkovskaya D. (2006) Neural networks, genetic algorithms and fuzzy system per. from Polish. I.D. Rudinsky. D. Rutkovskaya, М. Pilinsky, L. Rutkowski. Hotline Telecom. 452 p.

Published

21-12-2016

How to Cite

Potapov, V. (2016). CLASSIFICATION OF NEURAL NETWORK FOR TECHNICAL CONDITION OF TURBOFAN ENGINES BASED ON HYBRID ALGORITHM. Advances in Aerospace Technology, 69(4), 64–68. https://doi.org/10.18372/2306-1472.69.11057

Issue

Section

MODERN AVIATION AND SPACE TEHNOLOGY