Wavelet neural network PID controller for a UAS transporting a cable-suspended load
| Autor: | Eduardo Steed Espinoza Quesada, Luis Rodolfo Garcia Carrillo, Ricardo A. Barron-Gomez, L. E. Ramos-Velasco |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
0209 industrial biotechnology
Engineering Wavelet neural network business.industry PID controller Control engineering 02 engineering and technology Task (computing) 020901 industrial engineering & automation Wavelet Control and Systems Engineering Control theory Position (vector) 0202 electrical engineering electronic engineering information engineering Trajectory 020201 artificial intelligence & image processing Suspended load business |
| Zdroj: | IFAC-PapersOnLine. 50:2335-2340 |
| ISSN: | 2405-8963 |
| DOI: | 10.1016/j.ifacol.2017.08.419 |
| Popis: | A novel model-free Adaptive Wavenet PID (AWPID)-based controller for enabling an Unmanned Aircraft System (UAS) to transport a cable suspended load of unknown characteristics is presented. The control design enables the UAS to perform a trajectory tracking task, based solely on the knowledge of the UAS position. The methodology is based on a novel framework, which identifies inverse error dynamics using a Wavelet Neural Network (WNN) with daughter Mexican hat wavelets activation functions. A real-time load transportation task consisting of a multi-rotorcraft UAS carrying a cable suspended load of unknown characteristics validates the effectiveness of the trajectory tracking control strategy, showing smooth control signals even when the dynamic model of the UAS and the load characteristics are not known. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|