1. Neural Networks Attitude Decoupling Controller Design of Dual-Ducted SUAV Based on ADRC System
- Author
-
Dong Dong Wang, Tong Yue Gao, Tao Fei, and Hai Lang Ge
- Subjects
Engineering ,Control algorithm ,Artificial neural network ,business.industry ,Multivariable calculus ,General Engineering ,Control engineering ,Attitude control ,Nonlinear system ,Control theory ,Decoupling controller ,Strong coupling ,business ,Decoupling (electronics) - Abstract
This dual-ducted SUAV is a nonlinear and strong coupling of multiple-input and multiple-output system, and particularly between the pitch and roll channels channel coupling is strong, in order to implement effective control, it must be decoupled. The traditional methods are difficult to achieve effective control of the strong coupling of multivariable systems. Neural network which has a strong learning ability, is able to learn from the sample and can adapt to changing learning condition. Thus, the neural network can be used to simulate the learning process of operator, and operating characteristics information of objects can be excavated from the measured data, and accordingly change the parameters of the controller and decoupling network. This paper presents a attitude control algorithm of the dual-ducted SUAV which combine ADRC algorithms with neural network decoupling control algorithm, to design a SUAV decoupling controller. The simulation results showed that the attitude control channels between the pitch and roll were independently of each other, indicating a good solution to decouple the coupling between the pitch and roll channels based on neural network algorithm.
- Published
- 2014
- Full Text
- View/download PDF