INTELLIGENT SYSTEM OF HELICOPTER PILOTS SIMULATOR TRAINING

Authors

  • V. M. Sineglazov National Aviation University, Kyiv
  • V. O. Glukhov National Aviation University, Kyiv

DOI:

https://doi.org/10.18372/1990-5548.54.12325

Keywords:

Simulator training, intelligent system, artificial neural network, knowledge base

Abstract

The construction of an intelligent training system for helicopter pilots is under consideration. In the article the structural scheme of the simulator is developed, which includes the intellectual part that implements the process of selection of pilots, the adaptation of training assignments to the individual characteristics of the pilots, with the calculation of optimal training times and the number of repetitions of tasks, with the goal of forming stable helicopter control skills and knowledge control. Creation of tasks is carried out based on the usage of knowledge bases. As intellectual elements, artificial neural networks are used, in particular, a multi-layer perseptron and a Kohonen networks. The learning algorithm for Kohonen networks is given. To calculate the optimal training time and the number of repetitions of individual skills, mathematical models of the learning process have been developed.

Author Biographies

V. M. Sineglazov, National Aviation University, Kyiv

Aviation Computer-Integrated Complexes Department, Education & Scientific Institute of Information-Diagnostics Systems

Doctor of Engineering Science. Professor

V. O. Glukhov, National Aviation University, Kyiv

Aviation Computer-Integrated Complexes Department, Education & Scientific Institute of Information-Diagnostics Systems

Bachelor

References

T. Kohonen, Self-organizing maps. 3-rd Eng. publ. Moscow: BINOM, Knowledge laboratory, 2011, 655 p.

A. A. Mitsel and A. A. Poguda, “Neural Networks approach to the testing problem,” Applied informatics. no. 5 (35), pp. 60–67, 2011.

A. A. Mitsel and A. A. Poguda, “Technology of information processing at testing problems based on neural networks,” Modern educational space: ways of modernization: works of Internationl scientific-practical conference. Cheboksary. 2011, pp. 122–127.

Ju. M. Shmelev, “The optimal redistribution time of simulator training,” IEEE 3rd International Conference “Methods and Systems of Navigation and Motion Control (MSNMC)”. Proceedings. Kyiv, Ukraine. (October 14–17, 2014), Kyiv: NAU, 2014, pp. 75–78.

V. M. Sineglazov and Ju. M. Shmelev, “Improving the efficiency of helicopter pilots training in the simulator,” Electronics and Control Systems, no. 3(37), Kyiv: NAU, pp. 120–123, 2013.

V. M. Sineglazov and Ju. M. Shmelev, “Simulator training optimization,” Electronics and Control Systems, no. 1(39), Kyiv: NAU, pp. 63–66, 2014.

V. M. Sineglazov and Ju. M. Shmelev, “Estimation of helicopter pilots training efficiency in the simulator,” Electronics and Control Systems, no. 4(38), Kyiv: NAU, pp. 104–107, 2013.

A. A. Verbitskiy, V. N. Gridin, and I. V. Solodovnikov, “Neural Networks usage at problem of testing,” Informational technologies, no. 9, pp. 21–26, 2007.

https://Neuronus.com/theory/961-nejronnye-seti-kokhonena.html

Downloads

Issue

Vol. 4 No. 54 (2017)

Section

TRANSPORT SYSTEMS

License

Authors who publish with this journal agree to the following terms:

Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).