Journal article 359 views
A Novel BSO Algorithm for Three-Layer Neural Network Optimization Applied to UAV Edge Control
,
Zhaotian Fang,
Shuai Li
Neural Processing Letters, Volume: 55, Issue: 5, Pages: 6733 - 6752
Swansea University Author:
Shuai Li
Full text not available from this repository: check for access using links below.
DOI (Published version): 10.1007/s11063-023-11157-9
Abstract
Unmanned aerial vehicle is an unmanned aircraft operated by radio remote control equipment and self-provided program control device. The flight control system is the core of the entire flight process of unmanned aerial vehicle to complete take-off, mission execution and recovery. The classical propo...
| Published in: | Neural Processing Letters |
|---|---|
| ISSN: | 1370-4621 1573-773X |
| Published: |
Springer Science and Business Media LLC
2023
|
| Online Access: |
Check full text
|
| URI: | https://cronfa.swan.ac.uk/Record/cronfa62579 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract: |
Unmanned aerial vehicle is an unmanned aircraft operated by radio remote control equipment and self-provided program control device. The flight control system is the core of the entire flight process of unmanned aerial vehicle to complete take-off, mission execution and recovery. The classical proportion integral differential controller is widely used in the modern control field because of its simple principle and flexible implementation. However, tuning proportion integral differential parameters depends on lots of experience. In this paper, a three-layer feedforward neural network is proposed and used to stabilize the unmanned aerial vehicle edge control system. A novel weight and structure determination method that incorporates bionic beetle swarm optimization algorithm, called beetle swarm optimization weight and structure determination algorithm, is proposed to train the three-layer neural network. Furthermore, the sigmoid activation functions are utilized in the beetle swarm optimization weight and structure determination algorithm to identify the ideal weight and structure of the neural network when dealing with fitting and validation. Then, other five algorithms are added for the comparative analysis, namely particle swarm optimization algorithm, genetic algorithm, bat algorithm, firefly algorithm and artificial bee colony algorithm. In this way, the performance improvement of the beetle swarm optimization algorithm can be highlighted. Finally, the application of unmanned aerial vehicle edge control is given by using two different control methods respectively, i.e., the proportion integral differential controller and the beetle swarm optimization weight and structure determination neural network. It can be seen from the results that the beetle swarm optimization weight and structure determination neural network can enable the unmanned aerial vehicle to better achieve trajectory tracking by showing a better performance on edge control. |
|---|---|
| Keywords: |
Weight and structure determination (WASD) method, Control system, Neural networks, Beetle swarm optimization (BSO), UAV flight control |
| College: |
Faculty of Science and Engineering |
| Funders: |
This work was supported in part by the National Natural Science Foundation of China under Grant 62276085 and Grant 61906054, in part by the Natural Science Foundation of Zhejiang Province under Grant LY21-F030006. |
| Issue: |
5 |
| Start Page: |
6733 |
| End Page: |
6752 |