Problem statement. Measuring bases of two-coordinate phase direction finders (PDF), as a rule, are located along the same line, while bearing occurs in two planes independently. The procedure for determining the bearing in this case consists in restoring the true wave front and is quite computationally expensive. The study of PDF using a neural network with simultaneous use of information from all possible combinations of measurement bases is of particular interest from the point of view of evaluating the possibility of increasing the probability of correctly eliminating the ambiguity of bearing and increasing the accuracy of bearing, reducing computational costs and reducing the time to determine the bearing. Goal. Evaluation of the effectiveness of the use of artificial neural networks (NN) for direction finding of radio emission sources (RES) in solving radio monitoring problems using two-coordinate PDF, evaluation of the possibility of increasing the probability of correct elimination of ambiguity of bearing and increasing the accuracy of bearing when using all measuring bases of PDF. Results. A model of two-coordinate PDF based on NN has been developed, which makes it possible to evaluate the effectiveness of RES bearing in two planes with variations in model parameters and initial data. The obtained modeling results allow us to conclude that it is possible to create a two-coordinate PDF based on NN. The evaluation of the effectiveness of bearing shows that PDF based on NN has a commensurate accuracy of bearing and a high probability of eliminating ambiguity compared with PDF using classical methods and is somewhat inferior to them at high values of the phase measurement error in the receiving channels. Practical significance. The use of artificial neural networks (NN) for direction finding of radio emission sources (RES) in solving radio monitoring problems and further research on their development will improve the accuracy and reliability of measurements while reducing computational costs.
Read full abstract