| Author: | Jiang, Bailun |
| Title: | High precision tracking of UAV |
| Advisors: | Wen, Chih-yung (ME) Lu, Peng (ME) |
| Degree: | M.Sc. |
| Year: | 2021 |
| Subject: | Drone aircraft Drone aircraft -- Control systems Hong Kong Polytechnic University -- Dissertations |
| Department: | Department of Mechanical Engineering |
| Pages: | xii, 74 pages : color illustrations |
| Language: | English |
| Abstract: | In this dissertation, a Neural Network-based Model Predictive Control (NNMPC) method is proposed to control a quadrotor for trajectory tracking task. First, a detailed dynamic model including hub forces, rolling moment, and motor dynamics is derived. To verify the model, a PID controller and a simulation programme was designed by Simulink. A cascaded Model Predictive Control (MPC) controller is developed then. The controller is developed by simplified mathematical quadrotor model with position reference in three axes. In order to achieve neural network based control, modelling of quadrotor system for multi-step prediction with neural network is studied. A novel neural network modelling structure is proposed. Feed-Forward Neural Network (FFNN) and Nonlinear Auto-Regressive eXogenous (NARX) are adopted for prediction. Then, NNMPC are developed by using neural network prediction model in MPC. Simulation results show that NNMPC with neural network prediction model trained by flight data has good trajectory tracking performance. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 5924.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 4.23 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/11447