Open AccessМethod of automated development of solutions for special cases in flight
Author(s) -
A. V. Kolesnyk,
I. V. Zakharchenko,
R. V. Tarasov,
Поліна Берднік
Publication year - 2020
Publication title -
zv'âzok
Language(s) - English
Resource type - Journals
ISSN - 2412-9070
DOI - 10.31673/2412-9070.2020.052734
Subject(s) - computer science , probabilistic logic , bayesian network , process (computing) , machine learning , artificial intelligence , aviation , influence diagram , decision tree , operations research , engineering , aerospace engineering , operating system
The article develops a method of automated decision making in the framework of the creation of DSS air traffic controller. The method of automated decision-making for special cases in flight is being developed as one of the stages of information technology for the creation of decision support system for air traffic controllers. This is necessary to help decide on the option of terminating the flight in the event of a special case in flight on the example of engine failure on the aircraft. The developed method involves the use of probabilistic programming technology. It includes: construction of a probabilistic hierarchical model of emergency based on the Bayesian network taking into account the factors influencing the decision-making process, creating a sample of examples for learning the model to improve future situations models on examples using the Bayesian learning paradigm, the choice of inference algorithm to obtain a probabilistic conclusion. The proposed method is implemented in the probabilistic programming system Figaro, which is free and available under an open source license. The program code is written in Scala. The set of training data was formed based on the results of the investigation of aviation accidents and catastrophes and contained fifty-two cases of forced landing at the aerodrome and on the site with different consequences. The learning process was learning the parameters of the model on the data and was performed on thirty- six examples. Other cases (sixteen) were used to test the prediction quality of the created model. The Bayesian learning paradigm is used to teach the model, which does not require a special learning algorithm and is performed using the inference algorithm. The Metropolis-Hastings approximation algorithm is used as the derivation algorithm. The developed method showed high accuracy of forecasting. The error between the actual result and the estimate obtained using the Bayesian network was 10%. Further research will be aimed at developing information technology for the creation of DSS air traffic controller for special cases in flight.