Description: The subject of study of the article is the analysis of the means to ensure the improvement of the professional level of air traffic controllers through the use of simulators in the process of professional training. The purpose of the article. Presentation of the results of the development of a method of forming an information environment for training air traffic controllers in the process of simulator training for selecting initial conditions for displaying elements of the air situation based on the level of training and actions of air traffic controllers. The article proposes a method of forming an information environment for training air traffic controllers during simulator training. This method will allow to form the initial conditions for displaying the elements of the air situation of the corresponding information model, depending on the values of the input information. As input data for the fuzzy inference system, 5 initial values of the flight parameters of the aircraft were considered, presented in the form of minor linguistic changes: “azimuth”, “range”, “course”, “height”, “speed”, and as an output parameter - fuzzy linguistic variable “information elements of the air situation”. The COA method is used to account for overlapping areas of the set of rules that have been executed. Accordingly, the exit membership function is constructed by targeting the center of gravity of the skin exits from the rules that have been triggered. For fuzzy modeling of the process of choosing the option of displaying simulation elements of the air situation (information model), the MATLAB system is used in the work. Conclusion. The method of fuzzy inference according to the Mamdani algorithm for the formation of initial conditions for mapping elements of the air situation of the corresponding information model for its further simulation simulation in the simulator was further developed. The method differs from the known procedure of selecting various options for the formation of an information model on the set of information elements of the air situation, depending on the input data to the input of the simulator's intellectual system.
Keywords: air training controller, simulator, simulator training, intellectual system, information model.
1.Shuksunov, V.E., Tsibliyev, V.V. and Potocki, S.I. (2005), “Trenazhernye kompleksy i trenazhery: tekhnologiirazrab. i opyt ekspluatacii” [Training complexes and simulators: technologies developed. and operating experience], Engineer-ing, Moscow, 383 p.
2.Dushkov, B.A., Lomov, B.F. and Smirnov, B.A. (1991), “Hrestomatiya po inzhenernoj psihologii” [Textbook on engi-neering psychology], High School, Moscow, 287 p.
3.Krylov, A.A. (1988), “Ergonomika” [Ergonomics], Leningrad University, Leningrad, 184 р.
4.Magid, S.I., Zagretdinov, I.Sh., Mischeryakov, S.V., Arkhipova, E.N. and Musica, L.P. (2007), “Problemysovremennogo energeticheskogo trenazhyorostroeniya cherez prizmu terminologii” [Problems of modern energy simulators through the prism of terminology], Operational Management in the Power Industry, No. 1, pp. 35-51.
5.Pavlenko, M.A., Timochko, A.I., Stepanov, G.S. and Chernov, V.G. (2014), “Principles of building promising trainingsystems for the training of operators of automated control systems for dynamic objects” [Principles of building promising train-ing systems for the training of operators of automated control systems for dynamic objects], Modern information technologies in the field of security and defense, No. 1(19), pp. 112-117.
6.Nedelko, V.N. (2003), “Integrirovannaya urovnevaya baza znanij dlya sistem podderzhki prinyatiya reshenij real'nogovremeni” [Integrated Tier Knowledge Base for Real-Time Decision Support Systems], Artificial Intelligence, No. 4, pp. 335-341.
7.Niziyenko, B.I., Pavlenko, M.A., Shilo, S.G. and Berdnik, P.G. (2004), “Razrabotka metoda adaptivnogo upravleniyainformacionnymi modelyami v podsisteme informacionnogo obespecheniya processa prinyatiya resheniya po upravleniyu slozhnymi dinamicheskimi sistemami” [Development of a method for adaptive management of information models in the infor-mation support subsystem of the decision-making process for managing complex dynamic systems], Information Processing Systems, No. 11(39), pp. 125-140.
8.Wenda, V.F. (1982), “Inzhenernaya psihologiya i sintez sistem otobrazheniya informacii” [Engineering psychology andsynthesis of information display systems], Engineering, Moscow, 400 p.
9.Uskov, A.A. and Kruglov, V.V. (2003), “Intellektual'nye sistemy upravleniya na osnove metodov nechetkoj logiki” [In-telligent control systems based on fuzzy logic techniques], Smolensk City Printing House, Smolensk, 177 p.
10.Borisov, V.V. (1993), “Razrabotka metoda logicheskogo vyvoda dlya intellektual'noj sistemy podderzhki prinyatiyareshenij v shtabe obyedineniya PVO” [Development of a logical conclusion method for an intelligent decision support system at the headquarters of an air defense unit], Kharkiv, 242 p.
11.Scharf, H. Mandic, N. and Mamdani, E.H. (1986), A self-organizing algorithm for the control of a robot arm, Int. J.Robotics and Automation, No. 1(1), pp. 33-41.
12.Takagi, T. and Sugeno, M. (1985), Fuzzy Identification of Systems and Its Applications to Modeling and Control, IEEETrans. on Systems, Man, and Cybernetics, No. 15(1), pp. 116-132.
13.Averkin, A.N., Batyrshin, I.Z. and Blizhun, A.F. (1986), “Nechetkie mnozhestva v modelyah upravleniya iiskusstvennogo intellekta” [Fuzzy sets in control and artificial intelligence models], Science, Moscow, 312 p.
14.Leonenkov, A.V. (2005), “Nechetkoe modelirovanie v srede MATLAB и fuzzyTECH” [Fuzzy simulation in the environ-ment MATLAB и fuzzyTECH], BHV-Petersburg, Saint Petersburg, 716 р.