NEURAL NETWORK ALGORITHM SAFE OVERFLIGHT AERIAL OBSTACLES AND PROHIBITED LAND AREAS
The article presents the algorithm of safe flying around obstacles when making en route flight of manned and unmanned aircraft. The analysis of obstacles in the path of the aircraft is carried out. It is shown that the application of neural networks for this problem solving allows to increase the co...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
Moscow State Technical University of Civil Aviation
2017-09-01
|
| Series: | Научный вестник МГТУ ГА |
| Subjects: | |
| Online Access: | https://avia.mstuca.ru/jour/article/view/1114 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The article presents the algorithm of safe flying around obstacles when making en route flight of manned and unmanned aircraft. The analysis of obstacles in the path of the aircraft is carried out. It is shown that the application of neural networks for this problem solving allows to increase the control system performance and total flight safety. It is proved by modelling. The multilayer network consistent distribution is proposed to be used as neural network structure. In this work a neural network with three layers is used. To solve the problem the aircraft movement in plan is considered. It is important to have data on the Z coordinates of the obstacles vertices. Finally the number of neural network inputs was determined to be four. The number of alternatives, determining the number of neural network outputs is respectively five. As the continuing of the aircraft flight along the original route is possible, as a result, a training sample is in the form of a chart. After training the neural network simulations of its work were made. Obstacles have been formed in advance. |
|---|---|
| ISSN: | 2079-0619 2542-0119 |